diff --git a/rvc/embedders/.gitignore b/rvc/embedders/.gitignore
deleted file mode 100644
index 8b13789..0000000
--- a/rvc/embedders/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-
diff --git a/rvc/lib/FCPEF0Predictor.py b/rvc/lib/FCPEF0Predictor.py
deleted file mode 100644
index 02c7519..0000000
--- a/rvc/lib/FCPEF0Predictor.py
+++ /dev/null
@@ -1,1036 +0,0 @@
-from typing import Union
-
-import torch.nn.functional as F
-import numpy as np
-import torch
-import torch.nn as nn
-from torch.nn.utils.parametrizations import weight_norm
-from torchaudio.transforms import Resample
-import os
-import librosa
-import soundfile as sf
-import torch.utils.data
-from librosa.filters import mel as librosa_mel_fn
-import math
-from functools import partial
-
-from einops import rearrange, repeat
-from local_attention import LocalAttention
-from torch import nn
-
-os.environ["LRU_CACHE_CAPACITY"] = "3"
-
-
-def load_wav_to_torch(full_path, target_sr=None, return_empty_on_exception=False):
-    sample_rate = None
-    try:
-        data, sample_rate = sf.read(full_path, always_2d=True)  # than soundfile.
-    except Exception as error:
-        print(f"'{full_path}' failed to load with {error}")
-        if return_empty_on_exception:
-            return [], sample_rate or target_sr or 48000
-        else:
-            raise Exception(error)
-
-    if len(data.shape) > 1:
-        data = data[:, 0]
-        assert (
-            len(data) > 2
-        )  # check duration of audio file is > 2 samples (because otherwise the slice operation was on the wrong dimension)
-
-    if np.issubdtype(data.dtype, np.integer):  # if audio data is type int
-        max_mag = -np.iinfo(
-            data.dtype
-        ).min  # maximum magnitude = min possible value of intXX
-    else:  # if audio data is type fp32
-        max_mag = max(np.amax(data), -np.amin(data))
-        max_mag = (
-            (2**31) + 1
-            if max_mag > (2**15)
-            else ((2**15) + 1 if max_mag > 1.01 else 1.0)
-        )  # data should be either 16-bit INT, 32-bit INT or [-1 to 1] float32
-
-    data = torch.FloatTensor(data.astype(np.float32)) / max_mag
-
-    if (
-        torch.isinf(data) | torch.isnan(data)
-    ).any() and return_empty_on_exception:  # resample will crash with inf/NaN inputs. return_empty_on_exception will return empty arr instead of except
-        return [], sample_rate or target_sr or 48000
-    if target_sr is not None and sample_rate != target_sr:
-        data = torch.from_numpy(
-            librosa.core.resample(
-                data.numpy(), orig_sr=sample_rate, target_sr=target_sr
-            )
-        )
-        sample_rate = target_sr
-
-    return data, sample_rate
-
-
-def dynamic_range_compression(x, C=1, clip_val=1e-5):
-    return np.log(np.clip(x, a_min=clip_val, a_max=None) * C)
-
-
-def dynamic_range_decompression(x, C=1):
-    return np.exp(x) / C
-
-
-def dynamic_range_compression_torch(x, C=1, clip_val=1e-5):
-    return torch.log(torch.clamp(x, min=clip_val) * C)
-
-
-def dynamic_range_decompression_torch(x, C=1):
-    return torch.exp(x) / C
-
-
-class STFT:
-    def __init__(
-        self,
-        sr=22050,
-        n_mels=80,
-        n_fft=1024,
-        win_size=1024,
-        hop_length=256,
-        fmin=20,
-        fmax=11025,
-        clip_val=1e-5,
-    ):
-        self.target_sr = sr
-
-        self.n_mels = n_mels
-        self.n_fft = n_fft
-        self.win_size = win_size
-        self.hop_length = hop_length
-        self.fmin = fmin
-        self.fmax = fmax
-        self.clip_val = clip_val
-        self.mel_basis = {}
-        self.hann_window = {}
-
-    def get_mel(self, y, keyshift=0, speed=1, center=False, train=False):
-        sample_rate = self.target_sr
-        n_mels = self.n_mels
-        n_fft = self.n_fft
-        win_size = self.win_size
-        hop_length = self.hop_length
-        fmin = self.fmin
-        fmax = self.fmax
-        clip_val = self.clip_val
-
-        factor = 2 ** (keyshift / 12)
-        n_fft_new = int(np.round(n_fft * factor))
-        win_size_new = int(np.round(win_size * factor))
-        hop_length_new = int(np.round(hop_length * speed))
-        if not train:
-            mel_basis = self.mel_basis
-            hann_window = self.hann_window
-        else:
-            mel_basis = {}
-            hann_window = {}
-
-        mel_basis_key = str(fmax) + "_" + str(y.device)
-        if mel_basis_key not in mel_basis:
-            mel = librosa_mel_fn(
-                sr=sample_rate, n_fft=n_fft, n_mels=n_mels, fmin=fmin, fmax=fmax
-            )
-            mel_basis[mel_basis_key] = torch.from_numpy(mel).float().to(y.device)
-
-        keyshift_key = str(keyshift) + "_" + str(y.device)
-        if keyshift_key not in hann_window:
-            hann_window[keyshift_key] = torch.hann_window(win_size_new).to(y.device)
-
-        pad_left = (win_size_new - hop_length_new) // 2
-        pad_right = max(
-            (win_size_new - hop_length_new + 1) // 2,
-            win_size_new - y.size(-1) - pad_left,
-        )
-        if pad_right < y.size(-1):
-            mode = "reflect"
-        else:
-            mode = "constant"
-        y = torch.nn.functional.pad(y.unsqueeze(1), (pad_left, pad_right), mode=mode)
-        y = y.squeeze(1)
-
-        spec = torch.stft(
-            y,
-            n_fft_new,
-            hop_length=hop_length_new,
-            win_length=win_size_new,
-            window=hann_window[keyshift_key],
-            center=center,
-            pad_mode="reflect",
-            normalized=False,
-            onesided=True,
-            return_complex=True,
-        )
-        spec = torch.sqrt(spec.real.pow(2) + spec.imag.pow(2) + (1e-9))
-        if keyshift != 0:
-            size = n_fft // 2 + 1
-            resize = spec.size(1)
-            if resize < size:
-                spec = F.pad(spec, (0, 0, 0, size - resize))
-            spec = spec[:, :size, :] * win_size / win_size_new
-        spec = torch.matmul(mel_basis[mel_basis_key], spec)
-        spec = dynamic_range_compression_torch(spec, clip_val=clip_val)
-        return spec
-
-    def __call__(self, audiopath):
-        audio, sr = load_wav_to_torch(audiopath, target_sr=self.target_sr)
-        spect = self.get_mel(audio.unsqueeze(0)).squeeze(0)
-        return spect
-
-
-stft = STFT()
-
-# import fast_transformers.causal_product.causal_product_cuda
-
-
-def softmax_kernel(
-    data, *, projection_matrix, is_query, normalize_data=True, eps=1e-4, device=None
-):
-    b, h, *_ = data.shape
-    # (batch size, head, length, model_dim)
-
-    # normalize model dim
-    data_normalizer = (data.shape[-1] ** -0.25) if normalize_data else 1.0
-
-    # what is ration?, projection_matrix.shape[0] --> 266
-
-    ratio = projection_matrix.shape[0] ** -0.5
-
-    projection = repeat(projection_matrix, "j d -> b h j d", b=b, h=h)
-    projection = projection.type_as(data)
-
-    # data_dash = w^T x
-    data_dash = torch.einsum("...id,...jd->...ij", (data_normalizer * data), projection)
-
-    # diag_data = D**2
-    diag_data = data**2
-    diag_data = torch.sum(diag_data, dim=-1)
-    diag_data = (diag_data / 2.0) * (data_normalizer**2)
-    diag_data = diag_data.unsqueeze(dim=-1)
-
-    if is_query:
-        data_dash = ratio * (
-            torch.exp(
-                data_dash
-                - diag_data
-                - torch.max(data_dash, dim=-1, keepdim=True).values
-            )
-            + eps
-        )
-    else:
-        data_dash = ratio * (
-            torch.exp(data_dash - diag_data + eps)
-        )  # - torch.max(data_dash)) + eps)
-
-    return data_dash.type_as(data)
-
-
-def orthogonal_matrix_chunk(cols, qr_uniform_q=False, device=None):
-    unstructured_block = torch.randn((cols, cols), device=device)
-    q, r = torch.linalg.qr(unstructured_block.cpu(), mode="reduced")
-    q, r = map(lambda t: t.to(device), (q, r))
-
-    # proposed by @Parskatt
-    # to make sure Q is uniform https://arxiv.org/pdf/math-ph/0609050.pdf
-    if qr_uniform_q:
-        d = torch.diag(r, 0)
-        q *= d.sign()
-    return q.t()
-
-
-def exists(val):
-    return val is not None
-
-
-def empty(tensor):
-    return tensor.numel() == 0
-
-
-def default(val, d):
-    return val if exists(val) else d
-
-
-def cast_tuple(val):
-    return (val,) if not isinstance(val, tuple) else val
-
-
-class PCmer(nn.Module):
-    """The encoder that is used in the Transformer model."""
-
-    def __init__(
-        self,
-        num_layers,
-        num_heads,
-        dim_model,
-        dim_keys,
-        dim_values,
-        residual_dropout,
-        attention_dropout,
-    ):
-        super().__init__()
-        self.num_layers = num_layers
-        self.num_heads = num_heads
-        self.dim_model = dim_model
-        self.dim_values = dim_values
-        self.dim_keys = dim_keys
-        self.residual_dropout = residual_dropout
-        self.attention_dropout = attention_dropout
-
-        self._layers = nn.ModuleList([_EncoderLayer(self) for _ in range(num_layers)])
-
-    #  METHODS  ########################################################################################################
-
-    def forward(self, phone, mask=None):
-
-        # apply all layers to the input
-        for i, layer in enumerate(self._layers):
-            phone = layer(phone, mask)
-        # provide the final sequence
-        return phone
-
-
-# ==================================================================================================================== #
-#  CLASS  _ E N C O D E R  L A Y E R                                                                                   #
-# ==================================================================================================================== #
-
-
-class _EncoderLayer(nn.Module):
-    """One layer of the encoder.
-
-    Attributes:
-        attn: (:class:`mha.MultiHeadAttention`): The attention mechanism that is used to read the input sequence.
-        feed_forward (:class:`ffl.FeedForwardLayer`): The feed-forward layer on top of the attention mechanism.
-    """
-
-    def __init__(self, parent: PCmer):
-        """Creates a new instance of ``_EncoderLayer``.
-
-        Args:
-            parent (Encoder): The encoder that the layers is created for.
-        """
-        super().__init__()
-
-        self.conformer = ConformerConvModule(parent.dim_model)
-        self.norm = nn.LayerNorm(parent.dim_model)
-        self.dropout = nn.Dropout(parent.residual_dropout)
-
-        # selfatt -> fastatt: performer!
-        self.attn = SelfAttention(
-            dim=parent.dim_model, heads=parent.num_heads, causal=False
-        )
-
-    #  METHODS  ########################################################################################################
-
-    def forward(self, phone, mask=None):
-
-        # compute attention sub-layer
-        phone = phone + (self.attn(self.norm(phone), mask=mask))
-
-        phone = phone + (self.conformer(phone))
-
-        return phone
-
-
-def calc_same_padding(kernel_size):
-    pad = kernel_size // 2
-    return (pad, pad - (kernel_size + 1) % 2)
-
-
-# helper classes
-
-
-class Swish(nn.Module):
-    def forward(self, x):
-        return x * x.sigmoid()
-
-
-class Transpose(nn.Module):
-    def __init__(self, dims):
-        super().__init__()
-        assert len(dims) == 2, "dims must be a tuple of two dimensions"
-        self.dims = dims
-
-    def forward(self, x):
-        return x.transpose(*self.dims)
-
-
-class GLU(nn.Module):
-    def __init__(self, dim):
-        super().__init__()
-        self.dim = dim
-
-    def forward(self, x):
-        out, gate = x.chunk(2, dim=self.dim)
-        return out * gate.sigmoid()
-
-
-class DepthWiseConv1d(nn.Module):
-    def __init__(self, chan_in, chan_out, kernel_size, padding):
-        super().__init__()
-        self.padding = padding
-        self.conv = nn.Conv1d(chan_in, chan_out, kernel_size, groups=chan_in)
-
-    def forward(self, x):
-        x = F.pad(x, self.padding)
-        return self.conv(x)
-
-
-class ConformerConvModule(nn.Module):
-    def __init__(
-        self, dim, causal=False, expansion_factor=2, kernel_size=31, dropout=0.0
-    ):
-        super().__init__()
-
-        inner_dim = dim * expansion_factor
-        padding = calc_same_padding(kernel_size) if not causal else (kernel_size - 1, 0)
-
-        self.net = nn.Sequential(
-            nn.LayerNorm(dim),
-            Transpose((1, 2)),
-            nn.Conv1d(dim, inner_dim * 2, 1),
-            GLU(dim=1),
-            DepthWiseConv1d(
-                inner_dim, inner_dim, kernel_size=kernel_size, padding=padding
-            ),
-            # nn.BatchNorm1d(inner_dim) if not causal else nn.Identity(),
-            Swish(),
-            nn.Conv1d(inner_dim, dim, 1),
-            Transpose((1, 2)),
-            nn.Dropout(dropout),
-        )
-
-    def forward(self, x):
-        return self.net(x)
-
-
-def linear_attention(q, k, v):
-    if v is None:
-        out = torch.einsum("...ed,...nd->...ne", k, q)
-        return out
-
-    else:
-        k_cumsum = k.sum(dim=-2)
-        # k_cumsum = k.sum(dim = -2)
-        D_inv = 1.0 / (torch.einsum("...nd,...d->...n", q, k_cumsum.type_as(q)) + 1e-8)
-
-        context = torch.einsum("...nd,...ne->...de", k, v)
-        out = torch.einsum("...de,...nd,...n->...ne", context, q, D_inv)
-        return out
-
-
-def gaussian_orthogonal_random_matrix(
-    nb_rows, nb_columns, scaling=0, qr_uniform_q=False, device=None
-):
-    nb_full_blocks = int(nb_rows / nb_columns)
-    block_list = []
-
-    for _ in range(nb_full_blocks):
-        q = orthogonal_matrix_chunk(
-            nb_columns, qr_uniform_q=qr_uniform_q, device=device
-        )
-        block_list.append(q)
-
-    remaining_rows = nb_rows - nb_full_blocks * nb_columns
-    if remaining_rows > 0:
-        q = orthogonal_matrix_chunk(
-            nb_columns, qr_uniform_q=qr_uniform_q, device=device
-        )
-
-        block_list.append(q[:remaining_rows])
-
-    final_matrix = torch.cat(block_list)
-
-    if scaling == 0:
-        multiplier = torch.randn((nb_rows, nb_columns), device=device).norm(dim=1)
-    elif scaling == 1:
-        multiplier = math.sqrt((float(nb_columns))) * torch.ones(
-            (nb_rows,), device=device
-        )
-    else:
-        raise ValueError(f"Invalid scaling {scaling}")
-
-    return torch.diag(multiplier) @ final_matrix
-
-
-class FastAttention(nn.Module):
-    def __init__(
-        self,
-        dim_heads,
-        nb_features=None,
-        ortho_scaling=0,
-        causal=False,
-        generalized_attention=False,
-        kernel_fn=nn.ReLU(),
-        qr_uniform_q=False,
-        no_projection=False,
-    ):
-        super().__init__()
-        nb_features = default(nb_features, int(dim_heads * math.log(dim_heads)))
-
-        self.dim_heads = dim_heads
-        self.nb_features = nb_features
-        self.ortho_scaling = ortho_scaling
-
-        self.create_projection = partial(
-            gaussian_orthogonal_random_matrix,
-            nb_rows=self.nb_features,
-            nb_columns=dim_heads,
-            scaling=ortho_scaling,
-            qr_uniform_q=qr_uniform_q,
-        )
-        projection_matrix = self.create_projection()
-        self.register_buffer("projection_matrix", projection_matrix)
-
-        self.generalized_attention = generalized_attention
-        self.kernel_fn = kernel_fn
-
-        # if this is turned on, no projection will be used
-        # queries and keys will be softmax-ed as in the original efficient attention paper
-        self.no_projection = no_projection
-
-        self.causal = causal
-
-    @torch.no_grad()
-    def redraw_projection_matrix(self):
-        projections = self.create_projection()
-        self.projection_matrix.copy_(projections)
-        del projections
-
-    def forward(self, q, k, v):
-        device = q.device
-
-        if self.no_projection:
-            q = q.softmax(dim=-1)
-            k = torch.exp(k) if self.causal else k.softmax(dim=-2)
-        else:
-            create_kernel = partial(
-                softmax_kernel, projection_matrix=self.projection_matrix, device=device
-            )
-
-            q = create_kernel(q, is_query=True)
-            k = create_kernel(k, is_query=False)
-
-        attn_fn = linear_attention if not self.causal else self.causal_linear_fn
-        if v is None:
-            out = attn_fn(q, k, None)
-            return out
-        else:
-            out = attn_fn(q, k, v)
-            return out
-
-
-class SelfAttention(nn.Module):
-    def __init__(
-        self,
-        dim,
-        causal=False,
-        heads=8,
-        dim_head=64,
-        local_heads=0,
-        local_window_size=256,
-        nb_features=None,
-        feature_redraw_interval=1000,
-        generalized_attention=False,
-        kernel_fn=nn.ReLU(),
-        qr_uniform_q=False,
-        dropout=0.0,
-        no_projection=False,
-    ):
-        super().__init__()
-        assert dim % heads == 0, "dimension must be divisible by number of heads"
-        dim_head = default(dim_head, dim // heads)
-        inner_dim = dim_head * heads
-        self.fast_attention = FastAttention(
-            dim_head,
-            nb_features,
-            causal=causal,
-            generalized_attention=generalized_attention,
-            kernel_fn=kernel_fn,
-            qr_uniform_q=qr_uniform_q,
-            no_projection=no_projection,
-        )
-
-        self.heads = heads
-        self.global_heads = heads - local_heads
-        self.local_attn = (
-            LocalAttention(
-                window_size=local_window_size,
-                causal=causal,
-                autopad=True,
-                dropout=dropout,
-                look_forward=int(not causal),
-                rel_pos_emb_config=(dim_head, local_heads),
-            )
-            if local_heads > 0
-            else None
-        )
-
-        self.to_q = nn.Linear(dim, inner_dim)
-        self.to_k = nn.Linear(dim, inner_dim)
-        self.to_v = nn.Linear(dim, inner_dim)
-        self.to_out = nn.Linear(inner_dim, dim)
-        self.dropout = nn.Dropout(dropout)
-
-    @torch.no_grad()
-    def redraw_projection_matrix(self):
-        self.fast_attention.redraw_projection_matrix()
-
-    def forward(
-        self,
-        x,
-        context=None,
-        mask=None,
-        context_mask=None,
-        name=None,
-        inference=False,
-        **kwargs,
-    ):
-        _, _, _, h, gh = *x.shape, self.heads, self.global_heads
-
-        cross_attend = exists(context)
-
-        context = default(context, x)
-        context_mask = default(context_mask, mask) if not cross_attend else context_mask
-        q, k, v = self.to_q(x), self.to_k(context), self.to_v(context)
-
-        q, k, v = map(lambda t: rearrange(t, "b n (h d) -> b h n d", h=h), (q, k, v))
-        (q, lq), (k, lk), (v, lv) = map(lambda t: (t[:, :gh], t[:, gh:]), (q, k, v))
-
-        attn_outs = []
-        if not empty(q):
-            if exists(context_mask):
-                global_mask = context_mask[:, None, :, None]
-                v.masked_fill_(~global_mask, 0.0)
-            if cross_attend:
-                pass
-            else:
-                out = self.fast_attention(q, k, v)
-            attn_outs.append(out)
-
-        if not empty(lq):
-            assert (
-                not cross_attend
-            ), "local attention is not compatible with cross attention"
-            out = self.local_attn(lq, lk, lv, input_mask=mask)
-            attn_outs.append(out)
-
-        out = torch.cat(attn_outs, dim=1)
-        out = rearrange(out, "b h n d -> b n (h d)")
-        out = self.to_out(out)
-        return self.dropout(out)
-
-
-def l2_regularization(model, l2_alpha):
-    l2_loss = []
-    for module in model.modules():
-        if type(module) is nn.Conv2d:
-            l2_loss.append((module.weight**2).sum() / 2.0)
-    return l2_alpha * sum(l2_loss)
-
-
-class FCPE(nn.Module):
-    def __init__(
-        self,
-        input_channel=128,
-        out_dims=360,
-        n_layers=12,
-        n_chans=512,
-        use_siren=False,
-        use_full=False,
-        loss_mse_scale=10,
-        loss_l2_regularization=False,
-        loss_l2_regularization_scale=1,
-        loss_grad1_mse=False,
-        loss_grad1_mse_scale=1,
-        f0_max=1975.5,
-        f0_min=32.70,
-        confidence=False,
-        threshold=0.05,
-        use_input_conv=True,
-    ):
-        super().__init__()
-        if use_siren is True:
-            raise ValueError("Siren is not supported yet.")
-        if use_full is True:
-            raise ValueError("Full model is not supported yet.")
-
-        self.loss_mse_scale = loss_mse_scale if (loss_mse_scale is not None) else 10
-        self.loss_l2_regularization = (
-            loss_l2_regularization if (loss_l2_regularization is not None) else False
-        )
-        self.loss_l2_regularization_scale = (
-            loss_l2_regularization_scale
-            if (loss_l2_regularization_scale is not None)
-            else 1
-        )
-        self.loss_grad1_mse = loss_grad1_mse if (loss_grad1_mse is not None) else False
-        self.loss_grad1_mse_scale = (
-            loss_grad1_mse_scale if (loss_grad1_mse_scale is not None) else 1
-        )
-        self.f0_max = f0_max if (f0_max is not None) else 1975.5
-        self.f0_min = f0_min if (f0_min is not None) else 32.70
-        self.confidence = confidence if (confidence is not None) else False
-        self.threshold = threshold if (threshold is not None) else 0.05
-        self.use_input_conv = use_input_conv if (use_input_conv is not None) else True
-
-        self.cent_table_b = torch.Tensor(
-            np.linspace(
-                self.f0_to_cent(torch.Tensor([f0_min]))[0],
-                self.f0_to_cent(torch.Tensor([f0_max]))[0],
-                out_dims,
-            )
-        )
-        self.register_buffer("cent_table", self.cent_table_b)
-
-        # conv in stack
-        _leaky = nn.LeakyReLU()
-        self.stack = nn.Sequential(
-            nn.Conv1d(input_channel, n_chans, 3, 1, 1),
-            nn.GroupNorm(4, n_chans),
-            _leaky,
-            nn.Conv1d(n_chans, n_chans, 3, 1, 1),
-        )
-
-        # transformer
-        self.decoder = PCmer(
-            num_layers=n_layers,
-            num_heads=8,
-            dim_model=n_chans,
-            dim_keys=n_chans,
-            dim_values=n_chans,
-            residual_dropout=0.1,
-            attention_dropout=0.1,
-        )
-        self.norm = nn.LayerNorm(n_chans)
-
-        # out
-        self.n_out = out_dims
-        self.dense_out = weight_norm(nn.Linear(n_chans, self.n_out))
-
-    def forward(
-        self, mel, infer=True, gt_f0=None, return_hz_f0=False, cdecoder="local_argmax"
-    ):
-        """
-        input:
-            B x n_frames x n_unit
-        return:
-            dict of B x n_frames x feat
-        """
-        if cdecoder == "argmax":
-            self.cdecoder = self.cents_decoder
-        elif cdecoder == "local_argmax":
-            self.cdecoder = self.cents_local_decoder
-        if self.use_input_conv:
-            x = self.stack(mel.transpose(1, 2)).transpose(1, 2)
-        else:
-            x = mel
-        x = self.decoder(x)
-        x = self.norm(x)
-        x = self.dense_out(x)  # [B,N,D]
-        x = torch.sigmoid(x)
-        if not infer:
-            gt_cent_f0 = self.f0_to_cent(gt_f0)  # mel f0  #[B,N,1]
-            gt_cent_f0 = self.gaussian_blurred_cent(gt_cent_f0)  # #[B,N,out_dim]
-            loss_all = self.loss_mse_scale * F.binary_cross_entropy(
-                x, gt_cent_f0
-            )  # bce loss
-            # l2 regularization
-            if self.loss_l2_regularization:
-                loss_all = loss_all + l2_regularization(
-                    model=self, l2_alpha=self.loss_l2_regularization_scale
-                )
-            x = loss_all
-        if infer:
-            x = self.cdecoder(x)
-            x = self.cent_to_f0(x)
-            if not return_hz_f0:
-                x = (1 + x / 700).log()
-        return x
-
-    def cents_decoder(self, y, mask=True):
-        B, N, _ = y.size()
-        ci = self.cent_table[None, None, :].expand(B, N, -1)
-        rtn = torch.sum(ci * y, dim=-1, keepdim=True) / torch.sum(
-            y, dim=-1, keepdim=True
-        )  # cents: [B,N,1]
-        if mask:
-            confident = torch.max(y, dim=-1, keepdim=True)[0]
-            confident_mask = torch.ones_like(confident)
-            confident_mask[confident <= self.threshold] = float("-INF")
-            rtn = rtn * confident_mask
-        if self.confidence:
-            return rtn, confident
-        else:
-            return rtn
-
-    def cents_local_decoder(self, y, mask=True):
-        B, N, _ = y.size()
-        ci = self.cent_table[None, None, :].expand(B, N, -1)
-        confident, max_index = torch.max(y, dim=-1, keepdim=True)
-        local_argmax_index = torch.arange(0, 9).to(max_index.device) + (max_index - 4)
-        local_argmax_index[local_argmax_index < 0] = 0
-        local_argmax_index[local_argmax_index >= self.n_out] = self.n_out - 1
-        ci_l = torch.gather(ci, -1, local_argmax_index)
-        y_l = torch.gather(y, -1, local_argmax_index)
-        rtn = torch.sum(ci_l * y_l, dim=-1, keepdim=True) / torch.sum(
-            y_l, dim=-1, keepdim=True
-        )  # cents: [B,N,1]
-        if mask:
-            confident_mask = torch.ones_like(confident)
-            confident_mask[confident <= self.threshold] = float("-INF")
-            rtn = rtn * confident_mask
-        if self.confidence:
-            return rtn, confident
-        else:
-            return rtn
-
-    def cent_to_f0(self, cent):
-        return 10.0 * 2 ** (cent / 1200.0)
-
-    def f0_to_cent(self, f0):
-        return 1200.0 * torch.log2(f0 / 10.0)
-
-    def gaussian_blurred_cent(self, cents):  # cents: [B,N,1]
-        mask = (cents > 0.1) & (cents < (1200.0 * np.log2(self.f0_max / 10.0)))
-        B, N, _ = cents.size()
-        ci = self.cent_table[None, None, :].expand(B, N, -1)
-        return torch.exp(-torch.square(ci - cents) / 1250) * mask.float()
-
-
-class FCPEInfer:
-    def __init__(self, model_path, device=None, dtype=torch.float32):
-        if device is None:
-            device = "cuda" if torch.cuda.is_available() else "cpu"
-        self.device = device
-        ckpt = torch.load(model_path, map_location=torch.device(self.device))
-        self.args = DotDict(ckpt["config"])
-        self.dtype = dtype
-        model = FCPE(
-            input_channel=self.args.model.input_channel,
-            out_dims=self.args.model.out_dims,
-            n_layers=self.args.model.n_layers,
-            n_chans=self.args.model.n_chans,
-            use_siren=self.args.model.use_siren,
-            use_full=self.args.model.use_full,
-            loss_mse_scale=self.args.loss.loss_mse_scale,
-            loss_l2_regularization=self.args.loss.loss_l2_regularization,
-            loss_l2_regularization_scale=self.args.loss.loss_l2_regularization_scale,
-            loss_grad1_mse=self.args.loss.loss_grad1_mse,
-            loss_grad1_mse_scale=self.args.loss.loss_grad1_mse_scale,
-            f0_max=self.args.model.f0_max,
-            f0_min=self.args.model.f0_min,
-            confidence=self.args.model.confidence,
-        )
-        model.to(self.device).to(self.dtype)
-        model.load_state_dict(ckpt["model"])
-        model.eval()
-        self.model = model
-        self.wav2mel = Wav2Mel(self.args, dtype=self.dtype, device=self.device)
-
-    @torch.no_grad()
-    def __call__(self, audio, sr, threshold=0.05):
-        self.model.threshold = threshold
-        audio = audio[None, :]
-        mel = self.wav2mel(audio=audio, sample_rate=sr).to(self.dtype)
-        f0 = self.model(mel=mel, infer=True, return_hz_f0=True)
-        return f0
-
-
-class Wav2Mel:
-
-    def __init__(self, args, device=None, dtype=torch.float32):
-        # self.args = args
-        self.sample_rate = args.mel.sample_rate
-        self.hop_size = args.mel.hop_size
-        if device is None:
-            device = "cuda" if torch.cuda.is_available() else "cpu"
-        self.device = device
-        self.dtype = dtype
-        self.stft = STFT(
-            args.mel.sample_rate,
-            args.mel.num_mels,
-            args.mel.n_fft,
-            args.mel.win_size,
-            args.mel.hop_size,
-            args.mel.fmin,
-            args.mel.fmax,
-        )
-        self.resample_kernel = {}
-
-    def extract_nvstft(self, audio, keyshift=0, train=False):
-        mel = self.stft.get_mel(audio, keyshift=keyshift, train=train).transpose(
-            1, 2
-        )  # B, n_frames, bins
-        return mel
-
-    def extract_mel(self, audio, sample_rate, keyshift=0, train=False):
-        audio = audio.to(self.dtype).to(self.device)
-        # resample
-        if sample_rate == self.sample_rate:
-            audio_res = audio
-        else:
-            key_str = str(sample_rate)
-            if key_str not in self.resample_kernel:
-                self.resample_kernel[key_str] = Resample(
-                    sample_rate, self.sample_rate, lowpass_filter_width=128
-                )
-            self.resample_kernel[key_str] = (
-                self.resample_kernel[key_str].to(self.dtype).to(self.device)
-            )
-            audio_res = self.resample_kernel[key_str](audio)
-
-        # extract
-        mel = self.extract_nvstft(
-            audio_res, keyshift=keyshift, train=train
-        )  # B, n_frames, bins
-        n_frames = int(audio.shape[1] // self.hop_size) + 1
-        if n_frames > int(mel.shape[1]):
-            mel = torch.cat((mel, mel[:, -1:, :]), 1)
-        if n_frames < int(mel.shape[1]):
-            mel = mel[:, :n_frames, :]
-        return mel
-
-    def __call__(self, audio, sample_rate, keyshift=0, train=False):
-        return self.extract_mel(audio, sample_rate, keyshift=keyshift, train=train)
-
-
-class DotDict(dict):
-    def __getattr__(*args):
-        val = dict.get(*args)
-        return DotDict(val) if type(val) is dict else val
-
-    __setattr__ = dict.__setitem__
-    __delattr__ = dict.__delitem__
-
-
-class F0Predictor(object):
-    def compute_f0(self, wav, p_len):
-        """
-        input: wav:[signal_length]
-               p_len:int
-        output: f0:[signal_length//hop_length]
-        """
-        pass
-
-    def compute_f0_uv(self, wav, p_len):
-        """
-        input: wav:[signal_length]
-               p_len:int
-        output: f0:[signal_length//hop_length],uv:[signal_length//hop_length]
-        """
-        pass
-
-
-class FCPEF0Predictor(F0Predictor):
-    def __init__(
-        self,
-        model_path,
-        hop_length=512,
-        f0_min=50,
-        f0_max=1100,
-        dtype=torch.float32,
-        device=None,
-        sample_rate=44100,
-        threshold=0.05,
-    ):
-        self.fcpe = FCPEInfer(model_path, device=device, dtype=dtype)
-        self.hop_length = hop_length
-        self.f0_min = f0_min
-        self.f0_max = f0_max
-        if device is None:
-            self.device = "cuda" if torch.cuda.is_available() else "cpu"
-        else:
-            self.device = device
-        self.threshold = threshold
-        self.sample_rate = sample_rate
-        self.dtype = dtype
-        self.name = "fcpe"
-
-    def repeat_expand(
-        self,
-        content: Union[torch.Tensor, np.ndarray],
-        target_len: int,
-        mode: str = "nearest",
-    ):
-        ndim = content.ndim
-
-        if content.ndim == 1:
-            content = content[None, None]
-        elif content.ndim == 2:
-            content = content[None]
-
-        assert content.ndim == 3
-
-        is_np = isinstance(content, np.ndarray)
-        if is_np:
-            content = torch.from_numpy(content)
-
-        results = torch.nn.functional.interpolate(content, size=target_len, mode=mode)
-
-        if is_np:
-            results = results.numpy()
-
-        if ndim == 1:
-            return results[0, 0]
-        elif ndim == 2:
-            return results[0]
-
-    def post_process(self, x, sample_rate, f0, pad_to):
-        if isinstance(f0, np.ndarray):
-            f0 = torch.from_numpy(f0).float().to(x.device)
-
-        if pad_to is None:
-            return f0
-
-        f0 = self.repeat_expand(f0, pad_to)
-
-        vuv_vector = torch.zeros_like(f0)
-        vuv_vector[f0 > 0.0] = 1.0
-        vuv_vector[f0 <= 0.0] = 0.0
-
-        # 去掉0频率, 并线性插值
-        nzindex = torch.nonzero(f0).squeeze()
-        f0 = torch.index_select(f0, dim=0, index=nzindex).cpu().numpy()
-        time_org = self.hop_length / sample_rate * nzindex.cpu().numpy()
-        time_frame = np.arange(pad_to) * self.hop_length / sample_rate
-
-        vuv_vector = F.interpolate(vuv_vector[None, None, :], size=pad_to)[0][0]
-
-        if f0.shape[0] <= 0:
-            return (
-                torch.zeros(pad_to, dtype=torch.float, device=x.device).cpu().numpy(),
-                vuv_vector.cpu().numpy(),
-            )
-        if f0.shape[0] == 1:
-            return (
-                torch.ones(pad_to, dtype=torch.float, device=x.device) * f0[0]
-            ).cpu().numpy(), vuv_vector.cpu().numpy()
-
-        # 大概可以用 torch 重写?
-        f0 = np.interp(time_frame, time_org, f0, left=f0[0], right=f0[-1])
-        # vuv_vector = np.ceil(scipy.ndimage.zoom(vuv_vector,pad_to/len(vuv_vector),order = 0))
-
-        return f0, vuv_vector.cpu().numpy()
-
-    def compute_f0(self, wav, p_len=None):
-        x = torch.FloatTensor(wav).to(self.dtype).to(self.device)
-        if p_len is None:
-            print("fcpe p_len is None")
-            p_len = x.shape[0] // self.hop_length
-        f0 = self.fcpe(x, sr=self.sample_rate, threshold=self.threshold)[0, :, 0]
-        if torch.all(f0 == 0):
-            rtn = f0.cpu().numpy() if p_len is None else np.zeros(p_len)
-            return rtn, rtn
-        return self.post_process(x, self.sample_rate, f0, p_len)[0]
-
-    def compute_f0_uv(self, wav, p_len=None):
-        x = torch.FloatTensor(wav).to(self.dtype).to(self.device)
-        if p_len is None:
-            p_len = x.shape[0] // self.hop_length
-        f0 = self.fcpe(x, sr=self.sample_rate, threshold=self.threshold)[0, :, 0]
-        if torch.all(f0 == 0):
-            rtn = f0.cpu().numpy() if p_len is None else np.zeros(p_len)
-            return rtn, rtn
-        return self.post_process(x, self.sample_rate, f0, p_len)
diff --git a/rvc/lib/infer_pack/__init__.py b/rvc/lib/infer_pack/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/rvc/lib/infer_pack/attentions.py b/rvc/lib/infer_pack/attentions.py
deleted file mode 100644
index ea728e2..0000000
--- a/rvc/lib/infer_pack/attentions.py
+++ /dev/null
@@ -1,398 +0,0 @@
-import math
-import torch
-from torch import nn
-from torch.nn import functional as F
-
-from . import commons
-from .modules import LayerNorm
-
-
-class Encoder(nn.Module):
-    def __init__(
-        self,
-        hidden_channels,
-        filter_channels,
-        n_heads,
-        n_layers,
-        kernel_size=1,
-        p_dropout=0.0,
-        window_size=10,
-        **kwargs
-    ):
-        super().__init__()
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = p_dropout
-        self.window_size = window_size
-
-        self.drop = nn.Dropout(p_dropout)
-        self.attn_layers = nn.ModuleList()
-        self.norm_layers_1 = nn.ModuleList()
-        self.ffn_layers = nn.ModuleList()
-        self.norm_layers_2 = nn.ModuleList()
-        for i in range(self.n_layers):
-            self.attn_layers.append(
-                MultiHeadAttention(
-                    hidden_channels,
-                    hidden_channels,
-                    n_heads,
-                    p_dropout=p_dropout,
-                    window_size=window_size,
-                )
-            )
-            self.norm_layers_1.append(LayerNorm(hidden_channels))
-            self.ffn_layers.append(
-                FFN(
-                    hidden_channels,
-                    hidden_channels,
-                    filter_channels,
-                    kernel_size,
-                    p_dropout=p_dropout,
-                )
-            )
-            self.norm_layers_2.append(LayerNorm(hidden_channels))
-
-    def forward(self, x, x_mask):
-        attn_mask = x_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
-        x = x * x_mask
-        for i in range(self.n_layers):
-            y = self.attn_layers[i](x, x, attn_mask)
-            y = self.drop(y)
-            x = self.norm_layers_1[i](x + y)
-
-            y = self.ffn_layers[i](x, x_mask)
-            y = self.drop(y)
-            x = self.norm_layers_2[i](x + y)
-        x = x * x_mask
-        return x
-
-
-class Decoder(nn.Module):
-    def __init__(
-        self,
-        hidden_channels,
-        filter_channels,
-        n_heads,
-        n_layers,
-        kernel_size=1,
-        p_dropout=0.0,
-        proximal_bias=False,
-        proximal_init=True,
-        **kwargs
-    ):
-        super().__init__()
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = p_dropout
-        self.proximal_bias = proximal_bias
-        self.proximal_init = proximal_init
-
-        self.drop = nn.Dropout(p_dropout)
-        self.self_attn_layers = nn.ModuleList()
-        self.norm_layers_0 = nn.ModuleList()
-        self.encdec_attn_layers = nn.ModuleList()
-        self.norm_layers_1 = nn.ModuleList()
-        self.ffn_layers = nn.ModuleList()
-        self.norm_layers_2 = nn.ModuleList()
-        for i in range(self.n_layers):
-            self.self_attn_layers.append(
-                MultiHeadAttention(
-                    hidden_channels,
-                    hidden_channels,
-                    n_heads,
-                    p_dropout=p_dropout,
-                    proximal_bias=proximal_bias,
-                    proximal_init=proximal_init,
-                )
-            )
-            self.norm_layers_0.append(LayerNorm(hidden_channels))
-            self.encdec_attn_layers.append(
-                MultiHeadAttention(
-                    hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout
-                )
-            )
-            self.norm_layers_1.append(LayerNorm(hidden_channels))
-            self.ffn_layers.append(
-                FFN(
-                    hidden_channels,
-                    hidden_channels,
-                    filter_channels,
-                    kernel_size,
-                    p_dropout=p_dropout,
-                    causal=True,
-                )
-            )
-            self.norm_layers_2.append(LayerNorm(hidden_channels))
-
-    def forward(self, x, x_mask, h, h_mask):
-        """
-        x: decoder input
-        h: encoder output
-        """
-        self_attn_mask = commons.subsequent_mask(x_mask.size(2)).to(
-            device=x.device, dtype=x.dtype
-        )
-        encdec_attn_mask = h_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
-        x = x * x_mask
-        for i in range(self.n_layers):
-            y = self.self_attn_layers[i](x, x, self_attn_mask)
-            y = self.drop(y)
-            x = self.norm_layers_0[i](x + y)
-
-            y = self.encdec_attn_layers[i](x, h, encdec_attn_mask)
-            y = self.drop(y)
-            x = self.norm_layers_1[i](x + y)
-
-            y = self.ffn_layers[i](x, x_mask)
-            y = self.drop(y)
-            x = self.norm_layers_2[i](x + y)
-        x = x * x_mask
-        return x
-
-
-class MultiHeadAttention(nn.Module):
-    def __init__(
-        self,
-        channels,
-        out_channels,
-        n_heads,
-        p_dropout=0.0,
-        window_size=None,
-        heads_share=True,
-        block_length=None,
-        proximal_bias=False,
-        proximal_init=False,
-    ):
-        super().__init__()
-        assert channels % n_heads == 0
-
-        self.channels = channels
-        self.out_channels = out_channels
-        self.n_heads = n_heads
-        self.p_dropout = p_dropout
-        self.window_size = window_size
-        self.heads_share = heads_share
-        self.block_length = block_length
-        self.proximal_bias = proximal_bias
-        self.proximal_init = proximal_init
-        self.attn = None
-
-        self.k_channels = channels // n_heads
-        self.conv_q = nn.Conv1d(channels, channels, 1)
-        self.conv_k = nn.Conv1d(channels, channels, 1)
-        self.conv_v = nn.Conv1d(channels, channels, 1)
-        self.conv_o = nn.Conv1d(channels, out_channels, 1)
-        self.drop = nn.Dropout(p_dropout)
-
-        if window_size is not None:
-            n_heads_rel = 1 if heads_share else n_heads
-            rel_stddev = self.k_channels**-0.5
-            self.emb_rel_k = nn.Parameter(
-                torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
-                * rel_stddev
-            )
-            self.emb_rel_v = nn.Parameter(
-                torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
-                * rel_stddev
-            )
-
-        nn.init.xavier_uniform_(self.conv_q.weight)
-        nn.init.xavier_uniform_(self.conv_k.weight)
-        nn.init.xavier_uniform_(self.conv_v.weight)
-        if proximal_init:
-            with torch.no_grad():
-                self.conv_k.weight.copy_(self.conv_q.weight)
-                self.conv_k.bias.copy_(self.conv_q.bias)
-
-    def forward(self, x, c, attn_mask=None):
-        q = self.conv_q(x)
-        k = self.conv_k(c)
-        v = self.conv_v(c)
-
-        x, self.attn = self.attention(q, k, v, mask=attn_mask)
-
-        x = self.conv_o(x)
-        return x
-
-    def attention(self, query, key, value, mask=None):
-        b, d, t_s, t_t = (*key.size(), query.size(2))
-        query = query.view(b, self.n_heads, self.k_channels, t_t).transpose(2, 3)
-        key = key.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
-        value = value.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
-
-        scores = torch.matmul(query / math.sqrt(self.k_channels), key.transpose(-2, -1))
-        if self.window_size is not None:
-            assert (
-                t_s == t_t
-            ), "Relative attention is only available for self-attention."
-            key_relative_embeddings = self._get_relative_embeddings(self.emb_rel_k, t_s)
-            rel_logits = self._matmul_with_relative_keys(
-                query / math.sqrt(self.k_channels), key_relative_embeddings
-            )
-            scores_local = self._relative_position_to_absolute_position(rel_logits)
-            scores = scores + scores_local
-        if self.proximal_bias:
-            assert t_s == t_t, "Proximal bias is only available for self-attention."
-            scores = scores + self._attention_bias_proximal(t_s).to(
-                device=scores.device, dtype=scores.dtype
-            )
-        if mask is not None:
-            scores = scores.masked_fill(mask == 0, -1e4)
-            if self.block_length is not None:
-                assert (
-                    t_s == t_t
-                ), "Local attention is only available for self-attention."
-                block_mask = (
-                    torch.ones_like(scores)
-                    .triu(-self.block_length)
-                    .tril(self.block_length)
-                )
-                scores = scores.masked_fill(block_mask == 0, -1e4)
-        p_attn = F.softmax(scores, dim=-1)
-        p_attn = self.drop(p_attn)
-        output = torch.matmul(p_attn, value)
-        if self.window_size is not None:
-            relative_weights = self._absolute_position_to_relative_position(p_attn)
-            value_relative_embeddings = self._get_relative_embeddings(
-                self.emb_rel_v, t_s
-            )
-            output = output + self._matmul_with_relative_values(
-                relative_weights, value_relative_embeddings
-            )
-        output = output.transpose(2, 3).contiguous().view(b, d, t_t)
-        return output, p_attn
-
-    def _matmul_with_relative_values(self, x, y):
-        """
-        x: [b, h, l, m]
-        y: [h or 1, m, d]
-        ret: [b, h, l, d]
-        """
-        ret = torch.matmul(x, y.unsqueeze(0))
-        return ret
-
-    def _matmul_with_relative_keys(self, x, y):
-        """
-        x: [b, h, l, d]
-        y: [h or 1, m, d]
-        ret: [b, h, l, m]
-        """
-        ret = torch.matmul(x, y.unsqueeze(0).transpose(-2, -1))
-        return ret
-
-    def _get_relative_embeddings(self, relative_embeddings, length):
-        pad_length = max(length - (self.window_size + 1), 0)
-        slice_start_position = max((self.window_size + 1) - length, 0)
-        slice_end_position = slice_start_position + 2 * length - 1
-        if pad_length > 0:
-            padded_relative_embeddings = F.pad(
-                relative_embeddings,
-                commons.convert_pad_shape([[0, 0], [pad_length, pad_length], [0, 0]]),
-            )
-        else:
-            padded_relative_embeddings = relative_embeddings
-        used_relative_embeddings = padded_relative_embeddings[
-            :, slice_start_position:slice_end_position
-        ]
-        return used_relative_embeddings
-
-    def _relative_position_to_absolute_position(self, x):
-        """
-        x: [b, h, l, 2*l-1]
-        ret: [b, h, l, l]
-        """
-        batch, heads, length, _ = x.size()
-
-        x = F.pad(x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, 1]]))
-        x_flat = x.view([batch, heads, length * 2 * length])
-        x_flat = F.pad(
-            x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [0, length - 1]])
-        )
-
-        x_final = x_flat.view([batch, heads, length + 1, 2 * length - 1])[
-            :, :, :length, length - 1 :
-        ]
-        return x_final
-
-    def _absolute_position_to_relative_position(self, x):
-        """
-        x: [b, h, l, l]
-        ret: [b, h, l, 2*l-1]
-        """
-        batch, heads, length, _ = x.size()
-        x = F.pad(
-            x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, length - 1]])
-        )
-        x_flat = x.view([batch, heads, length**2 + length * (length - 1)])
-        x_flat = F.pad(x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [length, 0]]))
-        x_final = x_flat.view([batch, heads, length, 2 * length])[:, :, :, 1:]
-        return x_final
-
-    def _attention_bias_proximal(self, length):
-        r = torch.arange(length, dtype=torch.float32)
-        diff = torch.unsqueeze(r, 0) - torch.unsqueeze(r, 1)
-        return torch.unsqueeze(torch.unsqueeze(-torch.log1p(torch.abs(diff)), 0), 0)
-
-
-class FFN(nn.Module):
-    def __init__(
-        self,
-        in_channels,
-        out_channels,
-        filter_channels,
-        kernel_size,
-        p_dropout=0.0,
-        activation=None,
-        causal=False,
-    ):
-        super().__init__()
-        self.in_channels = in_channels
-        self.out_channels = out_channels
-        self.filter_channels = filter_channels
-        self.kernel_size = kernel_size
-        self.p_dropout = p_dropout
-        self.activation = activation
-        self.causal = causal
-
-        if causal:
-            self.padding = self._causal_padding
-        else:
-            self.padding = self._same_padding
-
-        self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size)
-        self.conv_2 = nn.Conv1d(filter_channels, out_channels, kernel_size)
-        self.drop = nn.Dropout(p_dropout)
-
-    def forward(self, x, x_mask):
-        x = self.conv_1(self.padding(x * x_mask))
-        if self.activation == "gelu":
-            x = x * torch.sigmoid(1.702 * x)
-        else:
-            x = torch.relu(x)
-        x = self.drop(x)
-        x = self.conv_2(self.padding(x * x_mask))
-        return x * x_mask
-
-    def _causal_padding(self, x):
-        if self.kernel_size == 1:
-            return x
-        pad_l = self.kernel_size - 1
-        pad_r = 0
-        padding = [[0, 0], [0, 0], [pad_l, pad_r]]
-        x = F.pad(x, commons.convert_pad_shape(padding))
-        return x
-
-    def _same_padding(self, x):
-        if self.kernel_size == 1:
-            return x
-        pad_l = (self.kernel_size - 1) // 2
-        pad_r = self.kernel_size // 2
-        padding = [[0, 0], [0, 0], [pad_l, pad_r]]
-        x = F.pad(x, commons.convert_pad_shape(padding))
-        return x
diff --git a/rvc/lib/infer_pack/commons.py b/rvc/lib/infer_pack/commons.py
deleted file mode 100644
index 5447098..0000000
--- a/rvc/lib/infer_pack/commons.py
+++ /dev/null
@@ -1,166 +0,0 @@
-import math
-import numpy as np
-import torch
-from torch import nn
-from torch.nn import functional as F
-
-
-def init_weights(m, mean=0.0, std=0.01):
-    classname = m.__class__.__name__
-    if classname.find("Conv") != -1:
-        m.weight.data.normal_(mean, std)
-
-
-def get_padding(kernel_size, dilation=1):
-    return int((kernel_size * dilation - dilation) / 2)
-
-
-def convert_pad_shape(pad_shape):
-    l = pad_shape[::-1]
-    pad_shape = [item for sublist in l for item in sublist]
-    return pad_shape
-
-
-def kl_divergence(m_p, logs_p, m_q, logs_q):
-    """KL(P||Q)"""
-    kl = (logs_q - logs_p) - 0.5
-    kl += (
-        0.5 * (torch.exp(2.0 * logs_p) + ((m_p - m_q) ** 2)) * torch.exp(-2.0 * logs_q)
-    )
-    return kl
-
-
-def rand_gumbel(shape):
-    """Sample from the Gumbel distribution, protect from overflows."""
-    uniform_samples = torch.rand(shape) * 0.99998 + 0.00001
-    return -torch.log(-torch.log(uniform_samples))
-
-
-def rand_gumbel_like(x):
-    g = rand_gumbel(x.size()).to(dtype=x.dtype, device=x.device)
-    return g
-
-
-def slice_segments(x, ids_str, segment_size=4):
-    ret = torch.zeros_like(x[:, :, :segment_size])
-    for i in range(x.size(0)):
-        idx_str = ids_str[i]
-        idx_end = idx_str + segment_size
-        ret[i] = x[i, :, idx_str:idx_end]
-    return ret
-
-
-def slice_segments2(x, ids_str, segment_size=4):
-    ret = torch.zeros_like(x[:, :segment_size])
-    for i in range(x.size(0)):
-        idx_str = ids_str[i]
-        idx_end = idx_str + segment_size
-        ret[i] = x[i, idx_str:idx_end]
-    return ret
-
-
-def rand_slice_segments(x, x_lengths=None, segment_size=4):
-    b, d, t = x.size()
-    if x_lengths is None:
-        x_lengths = t
-    ids_str_max = x_lengths - segment_size + 1
-    ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
-    ret = slice_segments(x, ids_str, segment_size)
-    return ret, ids_str
-
-
-def get_timing_signal_1d(length, channels, min_timescale=1.0, max_timescale=1.0e4):
-    position = torch.arange(length, dtype=torch.float)
-    num_timescales = channels // 2
-    log_timescale_increment = math.log(float(max_timescale) / float(min_timescale)) / (
-        num_timescales - 1
-    )
-    inv_timescales = min_timescale * torch.exp(
-        torch.arange(num_timescales, dtype=torch.float) * -log_timescale_increment
-    )
-    scaled_time = position.unsqueeze(0) * inv_timescales.unsqueeze(1)
-    signal = torch.cat([torch.sin(scaled_time), torch.cos(scaled_time)], 0)
-    signal = F.pad(signal, [0, 0, 0, channels % 2])
-    signal = signal.view(1, channels, length)
-    return signal
-
-
-def add_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4):
-    b, channels, length = x.size()
-    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
-    return x + signal.to(dtype=x.dtype, device=x.device)
-
-
-def cat_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4, axis=1):
-    b, channels, length = x.size()
-    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
-    return torch.cat([x, signal.to(dtype=x.dtype, device=x.device)], axis)
-
-
-def subsequent_mask(length):
-    mask = torch.tril(torch.ones(length, length)).unsqueeze(0).unsqueeze(0)
-    return mask
-
-
-@torch.jit.script
-def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
-    n_channels_int = n_channels[0]
-    in_act = input_a + input_b
-    t_act = torch.tanh(in_act[:, :n_channels_int, :])
-    s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
-    acts = t_act * s_act
-    return acts
-
-
-def convert_pad_shape(pad_shape):
-    l = pad_shape[::-1]
-    pad_shape = [item for sublist in l for item in sublist]
-    return pad_shape
-
-
-def shift_1d(x):
-    x = F.pad(x, convert_pad_shape([[0, 0], [0, 0], [1, 0]]))[:, :, :-1]
-    return x
-
-
-def sequence_mask(length, max_length=None):
-    if max_length is None:
-        max_length = length.max()
-    x = torch.arange(max_length, dtype=length.dtype, device=length.device)
-    return x.unsqueeze(0) < length.unsqueeze(1)
-
-
-def generate_path(duration, mask):
-    """
-    duration: [b, 1, t_x]
-    mask: [b, 1, t_y, t_x]
-    """
-    device = duration.device
-
-    b, _, t_y, t_x = mask.shape
-    cum_duration = torch.cumsum(duration, -1)
-
-    cum_duration_flat = cum_duration.view(b * t_x)
-    path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype)
-    path = path.view(b, t_x, t_y)
-    path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1]
-    path = path.unsqueeze(1).transpose(2, 3) * mask
-    return path
-
-
-def clip_grad_value_(parameters, clip_value, norm_type=2):
-    if isinstance(parameters, torch.Tensor):
-        parameters = [parameters]
-    parameters = list(filter(lambda p: p.grad is not None, parameters))
-    norm_type = float(norm_type)
-    if clip_value is not None:
-        clip_value = float(clip_value)
-
-    total_norm = 0
-    for p in parameters:
-        param_norm = p.grad.data.norm(norm_type)
-        total_norm += param_norm.item() ** norm_type
-        if clip_value is not None:
-            p.grad.data.clamp_(min=-clip_value, max=clip_value)
-    total_norm = total_norm ** (1.0 / norm_type)
-    return total_norm
diff --git a/rvc/lib/infer_pack/models.py b/rvc/lib/infer_pack/models.py
deleted file mode 100644
index 77a2b36..0000000
--- a/rvc/lib/infer_pack/models.py
+++ /dev/null
@@ -1,1382 +0,0 @@
-import math
-import torch
-from torch import nn
-from torch.nn import functional as F
-from . import modules
-from . import attentions
-from . import commons
-from .commons import init_weights, get_padding
-from torch.nn import Conv1d, ConvTranspose1d, Conv2d
-from torch.nn.utils import remove_weight_norm
-from torch.nn.utils.parametrizations import spectral_norm, weight_norm
-from typing import Optional
-
-has_xpu = bool(hasattr(torch, "xpu") and torch.xpu.is_available())
-
-
-class TextEncoder256(nn.Module):
-    def __init__(
-        self,
-        out_channels,
-        hidden_channels,
-        filter_channels,
-        n_heads,
-        n_layers,
-        kernel_size,
-        p_dropout,
-        f0=True,
-    ):
-        super(TextEncoder256, self).__init__()
-        self.out_channels = out_channels
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = float(p_dropout)
-        self.emb_phone = nn.Linear(256, hidden_channels)
-        self.lrelu = nn.LeakyReLU(0.1, inplace=True)
-        if f0 == True:
-            self.emb_pitch = nn.Embedding(256, hidden_channels)  # pitch 256
-        self.encoder = attentions.Encoder(
-            hidden_channels,
-            filter_channels,
-            n_heads,
-            n_layers,
-            kernel_size,
-            float(p_dropout),
-        )
-        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
-
-    def forward(
-        self, phone: torch.Tensor, pitch: Optional[torch.Tensor], lengths: torch.Tensor
-    ):
-        if pitch is None:
-            x = self.emb_phone(phone)
-        else:
-            x = self.emb_phone(phone) + self.emb_pitch(pitch)
-        x = x * math.sqrt(self.hidden_channels)  # [b, t, h]
-        x = self.lrelu(x)
-        x = torch.transpose(x, 1, -1)  # [b, h, t]
-        x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
-            x.dtype
-        )
-        x = self.encoder(x * x_mask, x_mask)
-        stats = self.proj(x) * x_mask
-
-        m, logs = torch.split(stats, self.out_channels, dim=1)
-        return m, logs, x_mask
-
-
-class TextEncoder768(nn.Module):
-    def __init__(
-        self,
-        out_channels,
-        hidden_channels,
-        filter_channels,
-        n_heads,
-        n_layers,
-        kernel_size,
-        p_dropout,
-        f0=True,
-    ):
-        super(TextEncoder768, self).__init__()
-        self.out_channels = out_channels
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = float(p_dropout)
-        self.emb_phone = nn.Linear(768, hidden_channels)
-        self.lrelu = nn.LeakyReLU(0.1, inplace=True)
-        if f0 == True:
-            self.emb_pitch = nn.Embedding(256, hidden_channels)  # pitch 256
-        self.encoder = attentions.Encoder(
-            hidden_channels,
-            filter_channels,
-            n_heads,
-            n_layers,
-            kernel_size,
-            float(p_dropout),
-        )
-        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
-
-    def forward(self, phone: torch.Tensor, pitch: torch.Tensor, lengths: torch.Tensor):
-        if pitch is None:
-            x = self.emb_phone(phone)
-        else:
-            x = self.emb_phone(phone) + self.emb_pitch(pitch)
-        x = x * math.sqrt(self.hidden_channels)  # [b, t, h]
-        x = self.lrelu(x)
-        x = torch.transpose(x, 1, -1)  # [b, h, t]
-        x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
-            x.dtype
-        )
-        x = self.encoder(x * x_mask, x_mask)
-        stats = self.proj(x) * x_mask
-
-        m, logs = torch.split(stats, self.out_channels, dim=1)
-        return m, logs, x_mask
-
-
-class ResidualCouplingBlock(nn.Module):
-    def __init__(
-        self,
-        channels,
-        hidden_channels,
-        kernel_size,
-        dilation_rate,
-        n_layers,
-        n_flows=4,
-        gin_channels=0,
-    ):
-        super(ResidualCouplingBlock, self).__init__()
-        self.channels = channels
-        self.hidden_channels = hidden_channels
-        self.kernel_size = kernel_size
-        self.dilation_rate = dilation_rate
-        self.n_layers = n_layers
-        self.n_flows = n_flows
-        self.gin_channels = gin_channels
-
-        self.flows = nn.ModuleList()
-        for i in range(n_flows):
-            self.flows.append(
-                modules.ResidualCouplingLayer(
-                    channels,
-                    hidden_channels,
-                    kernel_size,
-                    dilation_rate,
-                    n_layers,
-                    gin_channels=gin_channels,
-                    mean_only=True,
-                )
-            )
-            self.flows.append(modules.Flip())
-
-    def forward(
-        self,
-        x: torch.Tensor,
-        x_mask: torch.Tensor,
-        g: Optional[torch.Tensor] = None,
-        reverse: bool = False,
-    ):
-        if not reverse:
-            for flow in self.flows:
-                x, _ = flow(x, x_mask, g=g, reverse=reverse)
-        else:
-            for flow in self.flows[::-1]:
-                x = flow.forward(x, x_mask, g=g, reverse=reverse)
-        return x
-
-    def remove_weight_norm(self):
-        for i in range(self.n_flows):
-            self.flows[i * 2].remove_weight_norm()
-
-    def __prepare_scriptable__(self):
-        for i in range(self.n_flows):
-            for hook in self.flows[i * 2]._forward_pre_hooks.values():
-                if (
-                    hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                    and hook.__class__.__name__ == "WeightNorm"
-                ):
-                    torch.nn.utils.remove_weight_norm(self.flows[i * 2])
-
-        return self
-
-
-class PosteriorEncoder(nn.Module):
-    def __init__(
-        self,
-        in_channels,
-        out_channels,
-        hidden_channels,
-        kernel_size,
-        dilation_rate,
-        n_layers,
-        gin_channels=0,
-    ):
-        super(PosteriorEncoder, self).__init__()
-        self.in_channels = in_channels
-        self.out_channels = out_channels
-        self.hidden_channels = hidden_channels
-        self.kernel_size = kernel_size
-        self.dilation_rate = dilation_rate
-        self.n_layers = n_layers
-        self.gin_channels = gin_channels
-
-        self.pre = nn.Conv1d(in_channels, hidden_channels, 1)
-        self.enc = modules.WN(
-            hidden_channels,
-            kernel_size,
-            dilation_rate,
-            n_layers,
-            gin_channels=gin_channels,
-        )
-        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
-
-    def forward(
-        self, x: torch.Tensor, x_lengths: torch.Tensor, g: Optional[torch.Tensor] = None
-    ):
-        x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(
-            x.dtype
-        )
-        x = self.pre(x) * x_mask
-        x = self.enc(x, x_mask, g=g)
-        stats = self.proj(x) * x_mask
-        m, logs = torch.split(stats, self.out_channels, dim=1)
-        z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask
-        return z, m, logs, x_mask
-
-    def remove_weight_norm(self):
-        self.enc.remove_weight_norm()
-
-    def __prepare_scriptable__(self):
-        for hook in self.enc._forward_pre_hooks.values():
-            if (
-                hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                and hook.__class__.__name__ == "WeightNorm"
-            ):
-                torch.nn.utils.remove_weight_norm(self.enc)
-        return self
-
-
-class Generator(torch.nn.Module):
-    def __init__(
-        self,
-        initial_channel,
-        resblock,
-        resblock_kernel_sizes,
-        resblock_dilation_sizes,
-        upsample_rates,
-        upsample_initial_channel,
-        upsample_kernel_sizes,
-        gin_channels=0,
-    ):
-        super(Generator, self).__init__()
-        self.num_kernels = len(resblock_kernel_sizes)
-        self.num_upsamples = len(upsample_rates)
-        self.conv_pre = Conv1d(
-            initial_channel, upsample_initial_channel, 7, 1, padding=3
-        )
-        resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
-
-        self.ups = nn.ModuleList()
-        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
-            self.ups.append(
-                weight_norm(
-                    ConvTranspose1d(
-                        upsample_initial_channel // (2**i),
-                        upsample_initial_channel // (2 ** (i + 1)),
-                        k,
-                        u,
-                        padding=(k - u) // 2,
-                    )
-                )
-            )
-
-        self.resblocks = nn.ModuleList()
-        for i in range(len(self.ups)):
-            ch = upsample_initial_channel // (2 ** (i + 1))
-            for j, (k, d) in enumerate(
-                zip(resblock_kernel_sizes, resblock_dilation_sizes)
-            ):
-                self.resblocks.append(resblock(ch, k, d))
-
-        self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
-        self.ups.apply(init_weights)
-
-        if gin_channels != 0:
-            self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
-
-    def forward(self, x: torch.Tensor, g: Optional[torch.Tensor] = None):
-        x = self.conv_pre(x)
-        if g is not None:
-            x = x + self.cond(g)
-
-        for i in range(self.num_upsamples):
-            x = F.leaky_relu(x, modules.LRELU_SLOPE)
-            x = self.ups[i](x)
-            xs = None
-            for j in range(self.num_kernels):
-                if xs is None:
-                    xs = self.resblocks[i * self.num_kernels + j](x)
-                else:
-                    xs += self.resblocks[i * self.num_kernels + j](x)
-            x = xs / self.num_kernels
-        x = F.leaky_relu(x)
-        x = self.conv_post(x)
-        x = torch.tanh(x)
-
-        return x
-
-    def __prepare_scriptable__(self):
-        for l in self.ups:
-            for hook in l._forward_pre_hooks.values():
-                # The hook we want to remove is an instance of WeightNorm class, so
-                # normally we would do `if isinstance(...)` but this class is not accessible
-                # because of shadowing, so we check the module name directly.
-                # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
-                if (
-                    hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                    and hook.__class__.__name__ == "WeightNorm"
-                ):
-                    torch.nn.utils.remove_weight_norm(l)
-
-        for l in self.resblocks:
-            for hook in l._forward_pre_hooks.values():
-                if (
-                    hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                    and hook.__class__.__name__ == "WeightNorm"
-                ):
-                    torch.nn.utils.remove_weight_norm(l)
-        return self
-
-    def remove_weight_norm(self):
-        for l in self.ups:
-            remove_weight_norm(l)
-        for l in self.resblocks:
-            l.remove_weight_norm()
-
-
-class SineGen(torch.nn.Module):
-    """Definition of sine generator
-    SineGen(samp_rate, harmonic_num = 0,
-            sine_amp = 0.1, noise_std = 0.003,
-            voiced_threshold = 0,
-            flag_for_pulse=False)
-    samp_rate: sampling rate in Hz
-    harmonic_num: number of harmonic overtones (default 0)
-    sine_amp: amplitude of sine-wavefrom (default 0.1)
-    noise_std: std of Gaussian noise (default 0.003)
-    voiced_thoreshold: F0 threshold for U/V classification (default 0)
-    flag_for_pulse: this SinGen is used inside PulseGen (default False)
-    Note: when flag_for_pulse is True, the first time step of a voiced
-        segment is always sin(torch.pi) or cos(0)
-    """
-
-    def __init__(
-        self,
-        samp_rate,
-        harmonic_num=0,
-        sine_amp=0.1,
-        noise_std=0.003,
-        voiced_threshold=0,
-        flag_for_pulse=False,
-    ):
-        super(SineGen, self).__init__()
-        self.sine_amp = sine_amp
-        self.noise_std = noise_std
-        self.harmonic_num = harmonic_num
-        self.dim = self.harmonic_num + 1
-        self.sample_rate = samp_rate
-        self.voiced_threshold = voiced_threshold
-
-    def _f02uv(self, f0):
-        # generate uv signal
-        uv = torch.ones_like(f0)
-        uv = uv * (f0 > self.voiced_threshold)
-        if uv.device.type == "privateuseone":  # for DirectML
-            uv = uv.float()
-        return uv
-
-    def forward(self, f0: torch.Tensor, upp: int):
-        """sine_tensor, uv = forward(f0)
-        input F0: tensor(batchsize=1, length, dim=1)
-                  f0 for unvoiced steps should be 0
-        output sine_tensor: tensor(batchsize=1, length, dim)
-        output uv: tensor(batchsize=1, length, 1)
-        """
-        with torch.no_grad():
-            f0 = f0[:, None].transpose(1, 2)
-            f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim, device=f0.device)
-            # fundamental component
-            f0_buf[:, :, 0] = f0[:, :, 0]
-            for idx in range(self.harmonic_num):
-                f0_buf[:, :, idx + 1] = f0_buf[:, :, 0] * (
-                    idx + 2
-                )  # idx + 2: the (idx+1)-th overtone, (idx+2)-th harmonic
-            rad_values = (f0_buf / float(self.sample_rate)) % 1
-            rand_ini = torch.rand(
-                f0_buf.shape[0], f0_buf.shape[2], device=f0_buf.device
-            )
-            rand_ini[:, 0] = 0
-            rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini
-            tmp_over_one = torch.cumsum(rad_values, 1)
-            tmp_over_one *= upp
-            tmp_over_one = F.interpolate(
-                tmp_over_one.transpose(2, 1),
-                scale_factor=float(upp),
-                mode="linear",
-                align_corners=True,
-            ).transpose(2, 1)
-            rad_values = F.interpolate(
-                rad_values.transpose(2, 1), scale_factor=float(upp), mode="nearest"
-            ).transpose(
-                2, 1
-            )  #######
-            tmp_over_one %= 1
-            tmp_over_one_idx = (tmp_over_one[:, 1:, :] - tmp_over_one[:, :-1, :]) < 0
-            cumsum_shift = torch.zeros_like(rad_values)
-            cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0
-            sine_waves = torch.sin(
-                torch.cumsum(rad_values + cumsum_shift, dim=1) * 2 * torch.pi
-            )
-            sine_waves = sine_waves * self.sine_amp
-            uv = self._f02uv(f0)
-            uv = F.interpolate(
-                uv.transpose(2, 1), scale_factor=float(upp), mode="nearest"
-            ).transpose(2, 1)
-            noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3
-            noise = noise_amp * torch.randn_like(sine_waves)
-            sine_waves = sine_waves * uv + noise
-        return sine_waves, uv, noise
-
-
-class SourceModuleHnNSF(torch.nn.Module):
-    """SourceModule for hn-nsf
-    SourceModule(sample_rate, harmonic_num=0, sine_amp=0.1,
-                 add_noise_std=0.003, voiced_threshod=0)
-    sample_rate: sample_rate in Hz
-    harmonic_num: number of harmonic above F0 (default: 0)
-    sine_amp: amplitude of sine source signal (default: 0.1)
-    add_noise_std: std of additive Gaussian noise (default: 0.003)
-        note that amplitude of noise in unvoiced is decided
-        by sine_amp
-    voiced_threshold: threhold to set U/V given F0 (default: 0)
-    Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
-    F0_sampled (batchsize, length, 1)
-    Sine_source (batchsize, length, 1)
-    noise_source (batchsize, length 1)
-    uv (batchsize, length, 1)
-    """
-
-    def __init__(
-        self,
-        sample_rate,
-        harmonic_num=0,
-        sine_amp=0.1,
-        add_noise_std=0.003,
-        voiced_threshod=0,
-        is_half=True,
-    ):
-        super(SourceModuleHnNSF, self).__init__()
-
-        self.sine_amp = sine_amp
-        self.noise_std = add_noise_std
-        self.is_half = is_half
-        # to produce sine waveforms
-        self.l_sin_gen = SineGen(
-            sample_rate, harmonic_num, sine_amp, add_noise_std, voiced_threshod
-        )
-
-        # to merge source harmonics into a single excitation
-        self.l_linear = torch.nn.Linear(harmonic_num + 1, 1)
-        self.l_tanh = torch.nn.Tanh()
-        # self.ddtype:int = -1
-
-    def forward(self, x: torch.Tensor, upp: int = 1):
-        # if self.ddtype ==-1:
-        #     self.ddtype = self.l_linear.weight.dtype
-        sine_wavs, uv, _ = self.l_sin_gen(x, upp)
-        # print(x.dtype,sine_wavs.dtype,self.l_linear.weight.dtype)
-        # if self.is_half:
-        #     sine_wavs = sine_wavs.half()
-        # sine_merge = self.l_tanh(self.l_linear(sine_wavs.to(x)))
-        # print(sine_wavs.dtype,self.ddtype)
-        # if sine_wavs.dtype != self.l_linear.weight.dtype:
-        sine_wavs = sine_wavs.to(dtype=self.l_linear.weight.dtype)
-        sine_merge = self.l_tanh(self.l_linear(sine_wavs))
-        return sine_merge, None, None  # noise, uv
-
-
-class GeneratorNSF(torch.nn.Module):
-    def __init__(
-        self,
-        initial_channel,
-        resblock,
-        resblock_kernel_sizes,
-        resblock_dilation_sizes,
-        upsample_rates,
-        upsample_initial_channel,
-        upsample_kernel_sizes,
-        gin_channels,
-        sr,
-        is_half=False,
-    ):
-        super(GeneratorNSF, self).__init__()
-        self.num_kernels = len(resblock_kernel_sizes)
-        self.num_upsamples = len(upsample_rates)
-
-        self.f0_upsamp = torch.nn.Upsample(scale_factor=math.prod(upsample_rates))
-        self.m_source = SourceModuleHnNSF(
-            sample_rate=sr, harmonic_num=0, is_half=is_half
-        )
-        self.noise_convs = nn.ModuleList()
-        self.conv_pre = Conv1d(
-            initial_channel, upsample_initial_channel, 7, 1, padding=3
-        )
-        resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
-
-        self.ups = nn.ModuleList()
-        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
-            c_cur = upsample_initial_channel // (2 ** (i + 1))
-            self.ups.append(
-                weight_norm(
-                    ConvTranspose1d(
-                        upsample_initial_channel // (2**i),
-                        upsample_initial_channel // (2 ** (i + 1)),
-                        k,
-                        u,
-                        padding=(k - u) // 2,
-                    )
-                )
-            )
-            if i + 1 < len(upsample_rates):
-                stride_f0 = math.prod(upsample_rates[i + 1 :])
-                self.noise_convs.append(
-                    Conv1d(
-                        1,
-                        c_cur,
-                        kernel_size=stride_f0 * 2,
-                        stride=stride_f0,
-                        padding=stride_f0 // 2,
-                    )
-                )
-            else:
-                self.noise_convs.append(Conv1d(1, c_cur, kernel_size=1))
-
-        self.resblocks = nn.ModuleList()
-        for i in range(len(self.ups)):
-            ch = upsample_initial_channel // (2 ** (i + 1))
-            for j, (k, d) in enumerate(
-                zip(resblock_kernel_sizes, resblock_dilation_sizes)
-            ):
-                self.resblocks.append(resblock(ch, k, d))
-
-        self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
-        self.ups.apply(init_weights)
-
-        if gin_channels != 0:
-            self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
-
-        self.upp = math.prod(upsample_rates)
-
-        self.lrelu_slope = modules.LRELU_SLOPE
-
-    def forward(self, x, f0, g: Optional[torch.Tensor] = None):
-        har_source, noi_source, uv = self.m_source(f0, self.upp)
-        har_source = har_source.transpose(1, 2)
-        x = self.conv_pre(x)
-        if g is not None:
-            x = x + self.cond(g)
-        # torch.jit.script() does not support direct indexing of torch modules
-        # That's why I wrote this
-        for i, (ups, noise_convs) in enumerate(zip(self.ups, self.noise_convs)):
-            if i < self.num_upsamples:
-                x = F.leaky_relu(x, self.lrelu_slope)
-                x = ups(x)
-                x_source = noise_convs(har_source)
-                x = x + x_source
-                xs: Optional[torch.Tensor] = None
-                l = [i * self.num_kernels + j for j in range(self.num_kernels)]
-                for j, resblock in enumerate(self.resblocks):
-                    if j in l:
-                        if xs is None:
-                            xs = resblock(x)
-                        else:
-                            xs += resblock(x)
-                # This assertion cannot be ignored! \
-                # If ignored, it will cause torch.jit.script() compilation errors
-                assert isinstance(xs, torch.Tensor)
-                x = xs / self.num_kernels
-        x = F.leaky_relu(x)
-        x = self.conv_post(x)
-        x = torch.tanh(x)
-        return x
-
-    def remove_weight_norm(self):
-        for l in self.ups:
-            remove_weight_norm(l)
-        for l in self.resblocks:
-            l.remove_weight_norm()
-
-    def __prepare_scriptable__(self):
-        for l in self.ups:
-            for hook in l._forward_pre_hooks.values():
-                # The hook we want to remove is an instance of WeightNorm class, so
-                # normally we would do `if isinstance(...)` but this class is not accessible
-                # because of shadowing, so we check the module name directly.
-                # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
-                if (
-                    hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                    and hook.__class__.__name__ == "WeightNorm"
-                ):
-                    torch.nn.utils.remove_weight_norm(l)
-        for l in self.resblocks:
-            for hook in self.resblocks._forward_pre_hooks.values():
-                if (
-                    hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                    and hook.__class__.__name__ == "WeightNorm"
-                ):
-                    torch.nn.utils.remove_weight_norm(l)
-        return self
-
-
-class SynthesizerTrnMs256NSFsid(nn.Module):
-    def __init__(
-        self,
-        spec_channels,
-        segment_size,
-        inter_channels,
-        hidden_channels,
-        filter_channels,
-        n_heads,
-        n_layers,
-        kernel_size,
-        p_dropout,
-        resblock,
-        resblock_kernel_sizes,
-        resblock_dilation_sizes,
-        upsample_rates,
-        upsample_initial_channel,
-        upsample_kernel_sizes,
-        spk_embed_dim,
-        gin_channels,
-        sr,
-        **kwargs
-    ):
-        super(SynthesizerTrnMs256NSFsid, self).__init__()
-        self.spec_channels = spec_channels
-        self.inter_channels = inter_channels
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = float(p_dropout)
-        self.resblock = resblock
-        self.resblock_kernel_sizes = resblock_kernel_sizes
-        self.resblock_dilation_sizes = resblock_dilation_sizes
-        self.upsample_rates = upsample_rates
-        self.upsample_initial_channel = upsample_initial_channel
-        self.upsample_kernel_sizes = upsample_kernel_sizes
-        self.segment_size = segment_size
-        self.gin_channels = gin_channels
-        # self.hop_length = hop_length#
-        self.spk_embed_dim = spk_embed_dim
-        self.enc_p = TextEncoder256(
-            inter_channels,
-            hidden_channels,
-            filter_channels,
-            n_heads,
-            n_layers,
-            kernel_size,
-            float(p_dropout),
-        )
-        self.dec = GeneratorNSF(
-            inter_channels,
-            resblock,
-            resblock_kernel_sizes,
-            resblock_dilation_sizes,
-            upsample_rates,
-            upsample_initial_channel,
-            upsample_kernel_sizes,
-            gin_channels=gin_channels,
-            sr=sr,
-            is_half=kwargs["is_half"],
-        )
-        self.enc_q = PosteriorEncoder(
-            spec_channels,
-            inter_channels,
-            hidden_channels,
-            5,
-            1,
-            16,
-            gin_channels=gin_channels,
-        )
-        self.flow = ResidualCouplingBlock(
-            inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
-        )
-        self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
-
-    def remove_weight_norm(self):
-        self.dec.remove_weight_norm()
-        self.flow.remove_weight_norm()
-        self.enc_q.remove_weight_norm()
-
-    def __prepare_scriptable__(self):
-        for hook in self.dec._forward_pre_hooks.values():
-            # The hook we want to remove is an instance of WeightNorm class, so
-            # normally we would do `if isinstance(...)` but this class is not accessible
-            # because of shadowing, so we check the module name directly.
-            # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
-            if (
-                hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                and hook.__class__.__name__ == "WeightNorm"
-            ):
-                torch.nn.utils.remove_weight_norm(self.dec)
-        for hook in self.flow._forward_pre_hooks.values():
-            if (
-                hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                and hook.__class__.__name__ == "WeightNorm"
-            ):
-                torch.nn.utils.remove_weight_norm(self.flow)
-        if hasattr(self, "enc_q"):
-            for hook in self.enc_q._forward_pre_hooks.values():
-                if (
-                    hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                    and hook.__class__.__name__ == "WeightNorm"
-                ):
-                    torch.nn.utils.remove_weight_norm(self.enc_q)
-        return self
-
-    @torch.jit.ignore
-    def forward(
-        self,
-        phone: torch.Tensor,
-        phone_lengths: torch.Tensor,
-        pitch: torch.Tensor,
-        pitchf: torch.Tensor,
-        y: torch.Tensor,
-        y_lengths: torch.Tensor,
-        ds: Optional[torch.Tensor] = None,
-    ):  # 这里ds是id，[bs,1]
-        # print(1,pitch.shape)#[bs,t]
-        g = self.emb_g(ds).unsqueeze(-1)  # [b, 256, 1]##1是t，广播的
-        m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
-        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
-        z_p = self.flow(z, y_mask, g=g)
-        z_slice, ids_slice = commons.rand_slice_segments(
-            z, y_lengths, self.segment_size
-        )
-        # print(-1,pitchf.shape,ids_slice,self.segment_size,self.hop_length,self.segment_size//self.hop_length)
-        pitchf = commons.slice_segments2(pitchf, ids_slice, self.segment_size)
-        # print(-2,pitchf.shape,z_slice.shape)
-        o = self.dec(z_slice, pitchf, g=g)
-        return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
-
-    @torch.jit.export
-    def infer(
-        self,
-        phone: torch.Tensor,
-        phone_lengths: torch.Tensor,
-        pitch: torch.Tensor,
-        nsff0: torch.Tensor,
-        sid: torch.Tensor,
-        rate: Optional[torch.Tensor] = None,
-    ):
-        g = self.emb_g(sid).unsqueeze(-1)
-        m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
-        z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
-        if rate is not None:
-            assert isinstance(rate, torch.Tensor)
-            head = int(z_p.shape[2] * (1 - rate.item()))
-            z_p = z_p[:, :, head:]
-            x_mask = x_mask[:, :, head:]
-            nsff0 = nsff0[:, head:]
-        z = self.flow(z_p, x_mask, g=g, reverse=True)
-        o = self.dec(z * x_mask, nsff0, g=g)
-        return o, x_mask, (z, z_p, m_p, logs_p)
-
-
-class SynthesizerTrnMs768NSFsid(nn.Module):
-    def __init__(
-        self,
-        spec_channels,
-        segment_size,
-        inter_channels,
-        hidden_channels,
-        filter_channels,
-        n_heads,
-        n_layers,
-        kernel_size,
-        p_dropout,
-        resblock,
-        resblock_kernel_sizes,
-        resblock_dilation_sizes,
-        upsample_rates,
-        upsample_initial_channel,
-        upsample_kernel_sizes,
-        spk_embed_dim,
-        gin_channels,
-        sr,
-        **kwargs
-    ):
-        super(SynthesizerTrnMs768NSFsid, self).__init__()
-        self.spec_channels = spec_channels
-        self.inter_channels = inter_channels
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = float(p_dropout)
-        self.resblock = resblock
-        self.resblock_kernel_sizes = resblock_kernel_sizes
-        self.resblock_dilation_sizes = resblock_dilation_sizes
-        self.upsample_rates = upsample_rates
-        self.upsample_initial_channel = upsample_initial_channel
-        self.upsample_kernel_sizes = upsample_kernel_sizes
-        self.segment_size = segment_size
-        self.gin_channels = gin_channels
-        # self.hop_length = hop_length#
-        self.spk_embed_dim = spk_embed_dim
-        self.enc_p = TextEncoder768(
-            inter_channels,
-            hidden_channels,
-            filter_channels,
-            n_heads,
-            n_layers,
-            kernel_size,
-            float(p_dropout),
-        )
-        self.dec = GeneratorNSF(
-            inter_channels,
-            resblock,
-            resblock_kernel_sizes,
-            resblock_dilation_sizes,
-            upsample_rates,
-            upsample_initial_channel,
-            upsample_kernel_sizes,
-            gin_channels=gin_channels,
-            sr=sr,
-            is_half=kwargs["is_half"],
-        )
-        self.enc_q = PosteriorEncoder(
-            spec_channels,
-            inter_channels,
-            hidden_channels,
-            5,
-            1,
-            16,
-            gin_channels=gin_channels,
-        )
-        self.flow = ResidualCouplingBlock(
-            inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
-        )
-        self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
-
-    def remove_weight_norm(self):
-        self.dec.remove_weight_norm()
-        self.flow.remove_weight_norm()
-        self.enc_q.remove_weight_norm()
-
-    def __prepare_scriptable__(self):
-        for hook in self.dec._forward_pre_hooks.values():
-            # The hook we want to remove is an instance of WeightNorm class, so
-            # normally we would do `if isinstance(...)` but this class is not accessible
-            # because of shadowing, so we check the module name directly.
-            # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
-            if (
-                hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                and hook.__class__.__name__ == "WeightNorm"
-            ):
-                torch.nn.utils.remove_weight_norm(self.dec)
-        for hook in self.flow._forward_pre_hooks.values():
-            if (
-                hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                and hook.__class__.__name__ == "WeightNorm"
-            ):
-                torch.nn.utils.remove_weight_norm(self.flow)
-        if hasattr(self, "enc_q"):
-            for hook in self.enc_q._forward_pre_hooks.values():
-                if (
-                    hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                    and hook.__class__.__name__ == "WeightNorm"
-                ):
-                    torch.nn.utils.remove_weight_norm(self.enc_q)
-        return self
-
-    @torch.jit.ignore
-    def forward(
-        self, phone, phone_lengths, pitch, pitchf, y, y_lengths, ds
-    ):  # 这里ds是id，[bs,1]
-        # print(1,pitch.shape)#[bs,t]
-        g = self.emb_g(ds).unsqueeze(-1)  # [b, 256, 1]##1是t，广播的
-        m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
-        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
-        z_p = self.flow(z, y_mask, g=g)
-        z_slice, ids_slice = commons.rand_slice_segments(
-            z, y_lengths, self.segment_size
-        )
-        # print(-1,pitchf.shape,ids_slice,self.segment_size,self.hop_length,self.segment_size//self.hop_length)
-        pitchf = commons.slice_segments2(pitchf, ids_slice, self.segment_size)
-        # print(-2,pitchf.shape,z_slice.shape)
-        o = self.dec(z_slice, pitchf, g=g)
-        return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
-
-    @torch.jit.export
-    def infer(
-        self,
-        phone: torch.Tensor,
-        phone_lengths: torch.Tensor,
-        pitch: torch.Tensor,
-        nsff0: torch.Tensor,
-        sid: torch.Tensor,
-        rate: Optional[torch.Tensor] = None,
-    ):
-        g = self.emb_g(sid).unsqueeze(-1)
-        m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
-        z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
-        if rate is not None:
-            head = int(z_p.shape[2] * (1.0 - rate.item()))
-            z_p = z_p[:, :, head:]
-            x_mask = x_mask[:, :, head:]
-            nsff0 = nsff0[:, head:]
-        z = self.flow(z_p, x_mask, g=g, reverse=True)
-        o = self.dec(z * x_mask, nsff0, g=g)
-        return o, x_mask, (z, z_p, m_p, logs_p)
-
-
-class SynthesizerTrnMs256NSFsid_nono(nn.Module):
-    def __init__(
-        self,
-        spec_channels,
-        segment_size,
-        inter_channels,
-        hidden_channels,
-        filter_channels,
-        n_heads,
-        n_layers,
-        kernel_size,
-        p_dropout,
-        resblock,
-        resblock_kernel_sizes,
-        resblock_dilation_sizes,
-        upsample_rates,
-        upsample_initial_channel,
-        upsample_kernel_sizes,
-        spk_embed_dim,
-        gin_channels,
-        sr=None,
-        **kwargs
-    ):
-        super(SynthesizerTrnMs256NSFsid_nono, self).__init__()
-        self.spec_channels = spec_channels
-        self.inter_channels = inter_channels
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = float(p_dropout)
-        self.resblock = resblock
-        self.resblock_kernel_sizes = resblock_kernel_sizes
-        self.resblock_dilation_sizes = resblock_dilation_sizes
-        self.upsample_rates = upsample_rates
-        self.upsample_initial_channel = upsample_initial_channel
-        self.upsample_kernel_sizes = upsample_kernel_sizes
-        self.segment_size = segment_size
-        self.gin_channels = gin_channels
-        # self.hop_length = hop_length#
-        self.spk_embed_dim = spk_embed_dim
-        self.enc_p = TextEncoder256(
-            inter_channels,
-            hidden_channels,
-            filter_channels,
-            n_heads,
-            n_layers,
-            kernel_size,
-            float(p_dropout),
-            f0=False,
-        )
-        self.dec = Generator(
-            inter_channels,
-            resblock,
-            resblock_kernel_sizes,
-            resblock_dilation_sizes,
-            upsample_rates,
-            upsample_initial_channel,
-            upsample_kernel_sizes,
-            gin_channels=gin_channels,
-        )
-        self.enc_q = PosteriorEncoder(
-            spec_channels,
-            inter_channels,
-            hidden_channels,
-            5,
-            1,
-            16,
-            gin_channels=gin_channels,
-        )
-        self.flow = ResidualCouplingBlock(
-            inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
-        )
-        self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
-
-    def remove_weight_norm(self):
-        self.dec.remove_weight_norm()
-        self.flow.remove_weight_norm()
-        self.enc_q.remove_weight_norm()
-
-    def __prepare_scriptable__(self):
-        for hook in self.dec._forward_pre_hooks.values():
-            # The hook we want to remove is an instance of WeightNorm class, so
-            # normally we would do `if isinstance(...)` but this class is not accessible
-            # because of shadowing, so we check the module name directly.
-            # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
-            if (
-                hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                and hook.__class__.__name__ == "WeightNorm"
-            ):
-                torch.nn.utils.remove_weight_norm(self.dec)
-        for hook in self.flow._forward_pre_hooks.values():
-            if (
-                hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                and hook.__class__.__name__ == "WeightNorm"
-            ):
-                torch.nn.utils.remove_weight_norm(self.flow)
-        if hasattr(self, "enc_q"):
-            for hook in self.enc_q._forward_pre_hooks.values():
-                if (
-                    hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                    and hook.__class__.__name__ == "WeightNorm"
-                ):
-                    torch.nn.utils.remove_weight_norm(self.enc_q)
-        return self
-
-    @torch.jit.ignore
-    def forward(self, phone, phone_lengths, y, y_lengths, ds):  # 这里ds是id，[bs,1]
-        g = self.emb_g(ds).unsqueeze(-1)  # [b, 256, 1]##1是t，广播的
-        m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
-        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
-        z_p = self.flow(z, y_mask, g=g)
-        z_slice, ids_slice = commons.rand_slice_segments(
-            z, y_lengths, self.segment_size
-        )
-        o = self.dec(z_slice, g=g)
-        return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
-
-    @torch.jit.export
-    def infer(
-        self,
-        phone: torch.Tensor,
-        phone_lengths: torch.Tensor,
-        sid: torch.Tensor,
-        rate: Optional[torch.Tensor] = None,
-    ):
-        g = self.emb_g(sid).unsqueeze(-1)
-        m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
-        z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
-        if rate is not None:
-            head = int(z_p.shape[2] * (1.0 - rate.item()))
-            z_p = z_p[:, :, head:]
-            x_mask = x_mask[:, :, head:]
-        z = self.flow(z_p, x_mask, g=g, reverse=True)
-        o = self.dec(z * x_mask, g=g)
-        return o, x_mask, (z, z_p, m_p, logs_p)
-
-
-class SynthesizerTrnMs768NSFsid_nono(nn.Module):
-    def __init__(
-        self,
-        spec_channels,
-        segment_size,
-        inter_channels,
-        hidden_channels,
-        filter_channels,
-        n_heads,
-        n_layers,
-        kernel_size,
-        p_dropout,
-        resblock,
-        resblock_kernel_sizes,
-        resblock_dilation_sizes,
-        upsample_rates,
-        upsample_initial_channel,
-        upsample_kernel_sizes,
-        spk_embed_dim,
-        gin_channels,
-        sr=None,
-        **kwargs
-    ):
-        super(SynthesizerTrnMs768NSFsid_nono, self).__init__()
-        self.spec_channels = spec_channels
-        self.inter_channels = inter_channels
-        self.hidden_channels = hidden_channels
-        self.filter_channels = filter_channels
-        self.n_heads = n_heads
-        self.n_layers = n_layers
-        self.kernel_size = kernel_size
-        self.p_dropout = float(p_dropout)
-        self.resblock = resblock
-        self.resblock_kernel_sizes = resblock_kernel_sizes
-        self.resblock_dilation_sizes = resblock_dilation_sizes
-        self.upsample_rates = upsample_rates
-        self.upsample_initial_channel = upsample_initial_channel
-        self.upsample_kernel_sizes = upsample_kernel_sizes
-        self.segment_size = segment_size
-        self.gin_channels = gin_channels
-        # self.hop_length = hop_length#
-        self.spk_embed_dim = spk_embed_dim
-        self.enc_p = TextEncoder768(
-            inter_channels,
-            hidden_channels,
-            filter_channels,
-            n_heads,
-            n_layers,
-            kernel_size,
-            float(p_dropout),
-            f0=False,
-        )
-        self.dec = Generator(
-            inter_channels,
-            resblock,
-            resblock_kernel_sizes,
-            resblock_dilation_sizes,
-            upsample_rates,
-            upsample_initial_channel,
-            upsample_kernel_sizes,
-            gin_channels=gin_channels,
-        )
-        self.enc_q = PosteriorEncoder(
-            spec_channels,
-            inter_channels,
-            hidden_channels,
-            5,
-            1,
-            16,
-            gin_channels=gin_channels,
-        )
-        self.flow = ResidualCouplingBlock(
-            inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
-        )
-        self.emb_g = nn.Embedding(self.spk_embed_dim, gin_channels)
-
-    def remove_weight_norm(self):
-        self.dec.remove_weight_norm()
-        self.flow.remove_weight_norm()
-        self.enc_q.remove_weight_norm()
-
-    def __prepare_scriptable__(self):
-        for hook in self.dec._forward_pre_hooks.values():
-            # The hook we want to remove is an instance of WeightNorm class, so
-            # normally we would do `if isinstance(...)` but this class is not accessible
-            # because of shadowing, so we check the module name directly.
-            # https://github.com/pytorch/pytorch/blob/be0ca00c5ce260eb5bcec3237357f7a30cc08983/torch/nn/utils/__init__.py#L3
-            if (
-                hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                and hook.__class__.__name__ == "WeightNorm"
-            ):
-                torch.nn.utils.remove_weight_norm(self.dec)
-        for hook in self.flow._forward_pre_hooks.values():
-            if (
-                hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                and hook.__class__.__name__ == "WeightNorm"
-            ):
-                torch.nn.utils.remove_weight_norm(self.flow)
-        if hasattr(self, "enc_q"):
-            for hook in self.enc_q._forward_pre_hooks.values():
-                if (
-                    hook.__module__ == "torch.nn.utils.parametrizations.weight_norm"
-                    and hook.__class__.__name__ == "WeightNorm"
-                ):
-                    torch.nn.utils.remove_weight_norm(self.enc_q)
-        return self
-
-    @torch.jit.ignore
-    def forward(self, phone, phone_lengths, y, y_lengths, ds):  # 这里ds是id，[bs,1]
-        g = self.emb_g(ds).unsqueeze(-1)  # [b, 256, 1]##1是t，广播的
-        m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
-        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
-        z_p = self.flow(z, y_mask, g=g)
-        z_slice, ids_slice = commons.rand_slice_segments(
-            z, y_lengths, self.segment_size
-        )
-        o = self.dec(z_slice, g=g)
-        return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
-
-    @torch.jit.export
-    def infer(
-        self,
-        phone: torch.Tensor,
-        phone_lengths: torch.Tensor,
-        sid: torch.Tensor,
-        rate: Optional[torch.Tensor] = None,
-    ):
-        g = self.emb_g(sid).unsqueeze(-1)
-        m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
-        z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
-        if rate is not None:
-            head = int(z_p.shape[2] * (1.0 - rate.item()))
-            z_p = z_p[:, :, head:]
-            x_mask = x_mask[:, :, head:]
-        z = self.flow(z_p, x_mask, g=g, reverse=True)
-        o = self.dec(z * x_mask, g=g)
-        return o, x_mask, (z, z_p, m_p, logs_p)
-
-
-class MultiPeriodDiscriminator(torch.nn.Module):
-    def __init__(self, use_spectral_norm=False):
-        super(MultiPeriodDiscriminator, self).__init__()
-        periods = [2, 3, 5, 7, 11, 17]
-        # periods = [3, 5, 7, 11, 17, 23, 37]
-
-        discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
-        discs = discs + [
-            DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
-        ]
-        self.discriminators = nn.ModuleList(discs)
-
-    def forward(self, y, y_hat):
-        y_d_rs = []  #
-        y_d_gs = []
-        fmap_rs = []
-        fmap_gs = []
-        for i, d in enumerate(self.discriminators):
-            y_d_r, fmap_r = d(y)
-            y_d_g, fmap_g = d(y_hat)
-            # for j in range(len(fmap_r)):
-            #     print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
-            y_d_rs.append(y_d_r)
-            y_d_gs.append(y_d_g)
-            fmap_rs.append(fmap_r)
-            fmap_gs.append(fmap_g)
-
-        return y_d_rs, y_d_gs, fmap_rs, fmap_gs
-
-
-class MultiPeriodDiscriminatorV2(torch.nn.Module):
-    def __init__(self, use_spectral_norm=False):
-        super(MultiPeriodDiscriminatorV2, self).__init__()
-        # periods = [2, 3, 5, 7, 11, 17]
-        periods = [2, 3, 5, 7, 11, 17, 23, 37]
-
-        discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
-        discs = discs + [
-            DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
-        ]
-        self.discriminators = nn.ModuleList(discs)
-
-    def forward(self, y, y_hat):
-        y_d_rs = []  #
-        y_d_gs = []
-        fmap_rs = []
-        fmap_gs = []
-        for i, d in enumerate(self.discriminators):
-            y_d_r, fmap_r = d(y)
-            y_d_g, fmap_g = d(y_hat)
-            # for j in range(len(fmap_r)):
-            #     print(i,j,y.shape,y_hat.shape,fmap_r[j].shape,fmap_g[j].shape)
-            y_d_rs.append(y_d_r)
-            y_d_gs.append(y_d_g)
-            fmap_rs.append(fmap_r)
-            fmap_gs.append(fmap_g)
-
-        return y_d_rs, y_d_gs, fmap_rs, fmap_gs
-
-
-class DiscriminatorS(torch.nn.Module):
-    def __init__(self, use_spectral_norm=False):
-        super(DiscriminatorS, self).__init__()
-        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
-        self.convs = nn.ModuleList(
-            [
-                norm_f(Conv1d(1, 16, 15, 1, padding=7)),
-                norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)),
-                norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)),
-                norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)),
-                norm_f(Conv1d(1024, 1024, 41, 4, groups=256, padding=20)),
-                norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
-            ]
-        )
-        self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))
-
-    def forward(self, x):
-        fmap = []
-
-        for l in self.convs:
-            x = l(x)
-            x = F.leaky_relu(x, modules.LRELU_SLOPE)
-            fmap.append(x)
-        x = self.conv_post(x)
-        fmap.append(x)
-        x = torch.flatten(x, 1, -1)
-
-        return x, fmap
-
-
-class DiscriminatorP(torch.nn.Module):
-    def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False):
-        super(DiscriminatorP, self).__init__()
-        self.period = period
-        self.use_spectral_norm = use_spectral_norm
-        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
-        self.convs = nn.ModuleList(
-            [
-                norm_f(
-                    Conv2d(
-                        1,
-                        32,
-                        (kernel_size, 1),
-                        (stride, 1),
-                        padding=(get_padding(kernel_size, 1), 0),
-                    )
-                ),
-                norm_f(
-                    Conv2d(
-                        32,
-                        128,
-                        (kernel_size, 1),
-                        (stride, 1),
-                        padding=(get_padding(kernel_size, 1), 0),
-                    )
-                ),
-                norm_f(
-                    Conv2d(
-                        128,
-                        512,
-                        (kernel_size, 1),
-                        (stride, 1),
-                        padding=(get_padding(kernel_size, 1), 0),
-                    )
-                ),
-                norm_f(
-                    Conv2d(
-                        512,
-                        1024,
-                        (kernel_size, 1),
-                        (stride, 1),
-                        padding=(get_padding(kernel_size, 1), 0),
-                    )
-                ),
-                norm_f(
-                    Conv2d(
-                        1024,
-                        1024,
-                        (kernel_size, 1),
-                        1,
-                        padding=(get_padding(kernel_size, 1), 0),
-                    )
-                ),
-            ]
-        )
-        self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))
-
-    def forward(self, x):
-        fmap = []
-
-        # 1d to 2d
-        b, c, t = x.shape
-        if t % self.period != 0:  # pad first
-            n_pad = self.period - (t % self.period)
-            if has_xpu and x.dtype == torch.bfloat16:
-                x = F.pad(x.to(dtype=torch.float16), (0, n_pad), "reflect").to(
-                    dtype=torch.bfloat16
-                )
-            else:
-                x = F.pad(x, (0, n_pad), "reflect")
-            t = t + n_pad
-        x = x.view(b, c, t // self.period, self.period)
-
-        for l in self.convs:
-            x = l(x)
-            x = F.leaky_relu(x, modules.LRELU_SLOPE)
-            fmap.append(x)
-        x = self.conv_post(x)
-        fmap.append(x)
-        x = torch.flatten(x, 1, -1)
-
-        return x, fmap
diff --git a/rvc/lib/infer_pack/modules.py b/rvc/lib/infer_pack/modules.py
deleted file mode 100644
index 7c18733..0000000
--- a/rvc/lib/infer_pack/modules.py
+++ /dev/null
@@ -1,521 +0,0 @@
-import math
-import torch
-from torch import nn
-from torch.nn import functional as F
-
-from torch.nn import Conv1d
-from torch.nn.utils import remove_weight_norm
-from torch.nn.utils.parametrizations import weight_norm
-
-
-from . import commons
-from .commons import init_weights, get_padding
-from .transforms import piecewise_rational_quadratic_transform
-
-
-LRELU_SLOPE = 0.1
-
-
-class LayerNorm(nn.Module):
-    def __init__(self, channels, eps=1e-5):
-        super().__init__()
-        self.channels = channels
-        self.eps = eps
-
-        self.gamma = nn.Parameter(torch.ones(channels))
-        self.beta = nn.Parameter(torch.zeros(channels))
-
-    def forward(self, x):
-        x = x.transpose(1, -1)
-        x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps)
-        return x.transpose(1, -1)
-
-
-class ConvReluNorm(nn.Module):
-    def __init__(
-        self,
-        in_channels,
-        hidden_channels,
-        out_channels,
-        kernel_size,
-        n_layers,
-        p_dropout,
-    ):
-        super().__init__()
-        self.in_channels = in_channels
-        self.hidden_channels = hidden_channels
-        self.out_channels = out_channels
-        self.kernel_size = kernel_size
-        self.n_layers = n_layers
-        self.p_dropout = p_dropout
-        assert n_layers > 1, "Number of layers should be larger than 0."
-
-        self.conv_layers = nn.ModuleList()
-        self.norm_layers = nn.ModuleList()
-        self.conv_layers.append(
-            nn.Conv1d(
-                in_channels, hidden_channels, kernel_size, padding=kernel_size // 2
-            )
-        )
-        self.norm_layers.append(LayerNorm(hidden_channels))
-        self.relu_drop = nn.Sequential(nn.ReLU(), nn.Dropout(p_dropout))
-        for _ in range(n_layers - 1):
-            self.conv_layers.append(
-                nn.Conv1d(
-                    hidden_channels,
-                    hidden_channels,
-                    kernel_size,
-                    padding=kernel_size // 2,
-                )
-            )
-            self.norm_layers.append(LayerNorm(hidden_channels))
-        self.proj = nn.Conv1d(hidden_channels, out_channels, 1)
-        self.proj.weight.data.zero_()
-        self.proj.bias.data.zero_()
-
-    def forward(self, x, x_mask):
-        x_org = x
-        for i in range(self.n_layers):
-            x = self.conv_layers[i](x * x_mask)
-            x = self.norm_layers[i](x)
-            x = self.relu_drop(x)
-        x = x_org + self.proj(x)
-        return x * x_mask
-
-
-class DDSConv(nn.Module):
-    def __init__(self, channels, kernel_size, n_layers, p_dropout=0.0):
-        super().__init__()
-        self.channels = channels
-        self.kernel_size = kernel_size
-        self.n_layers = n_layers
-        self.p_dropout = p_dropout
-
-        self.drop = nn.Dropout(p_dropout)
-        self.convs_sep = nn.ModuleList()
-        self.convs_1x1 = nn.ModuleList()
-        self.norms_1 = nn.ModuleList()
-        self.norms_2 = nn.ModuleList()
-        for i in range(n_layers):
-            dilation = kernel_size**i
-            padding = (kernel_size * dilation - dilation) // 2
-            self.convs_sep.append(
-                nn.Conv1d(
-                    channels,
-                    channels,
-                    kernel_size,
-                    groups=channels,
-                    dilation=dilation,
-                    padding=padding,
-                )
-            )
-            self.convs_1x1.append(nn.Conv1d(channels, channels, 1))
-            self.norms_1.append(LayerNorm(channels))
-            self.norms_2.append(LayerNorm(channels))
-
-    def forward(self, x, x_mask, g=None):
-        if g is not None:
-            x = x + g
-        for i in range(self.n_layers):
-            y = self.convs_sep[i](x * x_mask)
-            y = self.norms_1[i](y)
-            y = F.gelu(y)
-            y = self.convs_1x1[i](y)
-            y = self.norms_2[i](y)
-            y = F.gelu(y)
-            y = self.drop(y)
-            x = x + y
-        return x * x_mask
-
-
-class WN(torch.nn.Module):
-    def __init__(
-        self,
-        hidden_channels,
-        kernel_size,
-        dilation_rate,
-        n_layers,
-        gin_channels=0,
-        p_dropout=0,
-    ):
-        super(WN, self).__init__()
-        assert kernel_size % 2 == 1
-        self.hidden_channels = hidden_channels
-        self.kernel_size = (kernel_size,)
-        self.dilation_rate = dilation_rate
-        self.n_layers = n_layers
-        self.gin_channels = gin_channels
-        self.p_dropout = p_dropout
-
-        self.in_layers = torch.nn.ModuleList()
-        self.res_skip_layers = torch.nn.ModuleList()
-        self.drop = nn.Dropout(p_dropout)
-
-        if gin_channels != 0:
-            cond_layer = torch.nn.Conv1d(
-                gin_channels, 2 * hidden_channels * n_layers, 1
-            )
-            self.cond_layer = torch.nn.utils.parametrizations.weight_norm(
-                cond_layer, name="weight"
-            )
-
-        for i in range(n_layers):
-            dilation = dilation_rate**i
-            padding = int((kernel_size * dilation - dilation) / 2)
-            in_layer = torch.nn.Conv1d(
-                hidden_channels,
-                2 * hidden_channels,
-                kernel_size,
-                dilation=dilation,
-                padding=padding,
-            )
-            in_layer = torch.nn.utils.parametrizations.weight_norm(
-                in_layer, name="weight"
-            )
-            self.in_layers.append(in_layer)
-            if i < n_layers - 1:
-                res_skip_channels = 2 * hidden_channels
-            else:
-                res_skip_channels = hidden_channels
-
-            res_skip_layer = torch.nn.Conv1d(hidden_channels, res_skip_channels, 1)
-            res_skip_layer = torch.nn.utils.parametrizations.weight_norm(
-                res_skip_layer, name="weight"
-            )
-            self.res_skip_layers.append(res_skip_layer)
-
-    def forward(self, x, x_mask, g=None, **kwargs):
-        output = torch.zeros_like(x)
-        n_channels_tensor = torch.IntTensor([self.hidden_channels])
-
-        if g is not None:
-            g = self.cond_layer(g)
-
-        for i in range(self.n_layers):
-            x_in = self.in_layers[i](x)
-            if g is not None:
-                cond_offset = i * 2 * self.hidden_channels
-                g_l = g[:, cond_offset : cond_offset + 2 * self.hidden_channels, :]
-            else:
-                g_l = torch.zeros_like(x_in)
-
-            acts = commons.fused_add_tanh_sigmoid_multiply(x_in, g_l, n_channels_tensor)
-            acts = self.drop(acts)
-
-            res_skip_acts = self.res_skip_layers[i](acts)
-            if i < self.n_layers - 1:
-                res_acts = res_skip_acts[:, : self.hidden_channels, :]
-                x = (x + res_acts) * x_mask
-                output = output + res_skip_acts[:, self.hidden_channels :, :]
-            else:
-                output = output + res_skip_acts
-        return output * x_mask
-
-    def remove_weight_norm(self):
-        if self.gin_channels != 0:
-            torch.nn.utils.remove_weight_norm(self.cond_layer)
-        for l in self.in_layers:
-            torch.nn.utils.remove_weight_norm(l)
-        for l in self.res_skip_layers:
-            torch.nn.utils.remove_weight_norm(l)
-
-
-class ResBlock1(torch.nn.Module):
-    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
-        super(ResBlock1, self).__init__()
-        self.convs1 = nn.ModuleList(
-            [
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        1,
-                        dilation=dilation[0],
-                        padding=get_padding(kernel_size, dilation[0]),
-                    )
-                ),
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        1,
-                        dilation=dilation[1],
-                        padding=get_padding(kernel_size, dilation[1]),
-                    )
-                ),
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        1,
-                        dilation=dilation[2],
-                        padding=get_padding(kernel_size, dilation[2]),
-                    )
-                ),
-            ]
-        )
-        self.convs1.apply(init_weights)
-
-        self.convs2 = nn.ModuleList(
-            [
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        1,
-                        dilation=1,
-                        padding=get_padding(kernel_size, 1),
-                    )
-                ),
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        1,
-                        dilation=1,
-                        padding=get_padding(kernel_size, 1),
-                    )
-                ),
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        1,
-                        dilation=1,
-                        padding=get_padding(kernel_size, 1),
-                    )
-                ),
-            ]
-        )
-        self.convs2.apply(init_weights)
-
-    def forward(self, x, x_mask=None):
-        for c1, c2 in zip(self.convs1, self.convs2):
-            xt = F.leaky_relu(x, LRELU_SLOPE)
-            if x_mask is not None:
-                xt = xt * x_mask
-            xt = c1(xt)
-            xt = F.leaky_relu(xt, LRELU_SLOPE)
-            if x_mask is not None:
-                xt = xt * x_mask
-            xt = c2(xt)
-            x = xt + x
-        if x_mask is not None:
-            x = x * x_mask
-        return x
-
-    def remove_weight_norm(self):
-        for l in self.convs1:
-            remove_weight_norm(l)
-        for l in self.convs2:
-            remove_weight_norm(l)
-
-
-class ResBlock2(torch.nn.Module):
-    def __init__(self, channels, kernel_size=3, dilation=(1, 3)):
-        super(ResBlock2, self).__init__()
-        self.convs = nn.ModuleList(
-            [
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        1,
-                        dilation=dilation[0],
-                        padding=get_padding(kernel_size, dilation[0]),
-                    )
-                ),
-                weight_norm(
-                    Conv1d(
-                        channels,
-                        channels,
-                        kernel_size,
-                        1,
-                        dilation=dilation[1],
-                        padding=get_padding(kernel_size, dilation[1]),
-                    )
-                ),
-            ]
-        )
-        self.convs.apply(init_weights)
-
-    def forward(self, x, x_mask=None):
-        for c in self.convs:
-            xt = F.leaky_relu(x, LRELU_SLOPE)
-            if x_mask is not None:
-                xt = xt * x_mask
-            xt = c(xt)
-            x = xt + x
-        if x_mask is not None:
-            x = x * x_mask
-        return x
-
-    def remove_weight_norm(self):
-        for l in self.convs:
-            remove_weight_norm(l)
-
-
-class Log(nn.Module):
-    def forward(self, x, x_mask, reverse=False, **kwargs):
-        if not reverse:
-            y = torch.log(torch.clamp_min(x, 1e-5)) * x_mask
-            logdet = torch.sum(-y, [1, 2])
-            return y, logdet
-        else:
-            x = torch.exp(x) * x_mask
-            return x
-
-
-class Flip(nn.Module):
-    def forward(self, x, *args, reverse=False, **kwargs):
-        x = torch.flip(x, [1])
-        if not reverse:
-            logdet = torch.zeros(x.size(0)).to(dtype=x.dtype, device=x.device)
-            return x, logdet
-        else:
-            return x
-
-
-class ElementwiseAffine(nn.Module):
-    def __init__(self, channels):
-        super().__init__()
-        self.channels = channels
-        self.m = nn.Parameter(torch.zeros(channels, 1))
-        self.logs = nn.Parameter(torch.zeros(channels, 1))
-
-    def forward(self, x, x_mask, reverse=False, **kwargs):
-        if not reverse:
-            y = self.m + torch.exp(self.logs) * x
-            y = y * x_mask
-            logdet = torch.sum(self.logs * x_mask, [1, 2])
-            return y, logdet
-        else:
-            x = (x - self.m) * torch.exp(-self.logs) * x_mask
-            return x
-
-
-class ResidualCouplingLayer(nn.Module):
-    def __init__(
-        self,
-        channels,
-        hidden_channels,
-        kernel_size,
-        dilation_rate,
-        n_layers,
-        p_dropout=0,
-        gin_channels=0,
-        mean_only=False,
-    ):
-        assert channels % 2 == 0, "channels should be divisible by 2"
-        super().__init__()
-        self.channels = channels
-        self.hidden_channels = hidden_channels
-        self.kernel_size = kernel_size
-        self.dilation_rate = dilation_rate
-        self.n_layers = n_layers
-        self.half_channels = channels // 2
-        self.mean_only = mean_only
-
-        self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
-        self.enc = WN(
-            hidden_channels,
-            kernel_size,
-            dilation_rate,
-            n_layers,
-            p_dropout=p_dropout,
-            gin_channels=gin_channels,
-        )
-        self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
-        self.post.weight.data.zero_()
-        self.post.bias.data.zero_()
-
-    def forward(self, x, x_mask, g=None, reverse=False):
-        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
-        h = self.pre(x0) * x_mask
-        h = self.enc(h, x_mask, g=g)
-        stats = self.post(h) * x_mask
-        if not self.mean_only:
-            m, logs = torch.split(stats, [self.half_channels] * 2, 1)
-        else:
-            m = stats
-            logs = torch.zeros_like(m)
-
-        if not reverse:
-            x1 = m + x1 * torch.exp(logs) * x_mask
-            x = torch.cat([x0, x1], 1)
-            logdet = torch.sum(logs, [1, 2])
-            return x, logdet
-        else:
-            x1 = (x1 - m) * torch.exp(-logs) * x_mask
-            x = torch.cat([x0, x1], 1)
-            return x
-
-    def remove_weight_norm(self):
-        self.enc.remove_weight_norm()
-
-
-class ConvFlow(nn.Module):
-    def __init__(
-        self,
-        in_channels,
-        filter_channels,
-        kernel_size,
-        n_layers,
-        num_bins=10,
-        tail_bound=5.0,
-    ):
-        super().__init__()
-        self.in_channels = in_channels
-        self.filter_channels = filter_channels
-        self.kernel_size = kernel_size
-        self.n_layers = n_layers
-        self.num_bins = num_bins
-        self.tail_bound = tail_bound
-        self.half_channels = in_channels // 2
-
-        self.pre = nn.Conv1d(self.half_channels, filter_channels, 1)
-        self.convs = DDSConv(filter_channels, kernel_size, n_layers, p_dropout=0.0)
-        self.proj = nn.Conv1d(
-            filter_channels, self.half_channels * (num_bins * 3 - 1), 1
-        )
-        self.proj.weight.data.zero_()
-        self.proj.bias.data.zero_()
-
-    def forward(self, x, x_mask, g=None, reverse=False):
-        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
-        h = self.pre(x0)
-        h = self.convs(h, x_mask, g=g)
-        h = self.proj(h) * x_mask
-
-        b, c, t = x0.shape
-        h = h.reshape(b, c, -1, t).permute(0, 1, 3, 2)
-
-        unnormalized_widths = h[..., : self.num_bins] / math.sqrt(self.filter_channels)
-        unnormalized_heights = h[..., self.num_bins : 2 * self.num_bins] / math.sqrt(
-            self.filter_channels
-        )
-        unnormalized_derivatives = h[..., 2 * self.num_bins :]
-
-        x1, logabsdet = piecewise_rational_quadratic_transform(
-            x1,
-            unnormalized_widths,
-            unnormalized_heights,
-            unnormalized_derivatives,
-            inverse=reverse,
-            tails="linear",
-            tail_bound=self.tail_bound,
-        )
-
-        x = torch.cat([x0, x1], 1) * x_mask
-        logdet = torch.sum(logabsdet * x_mask, [1, 2])
-        if not reverse:
-            return x, logdet
-        else:
-            return x
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/DioF0Predictor.py b/rvc/lib/infer_pack/modules/F0Predictor/DioF0Predictor.py
deleted file mode 100644
index e95c0e9..0000000
--- a/rvc/lib/infer_pack/modules/F0Predictor/DioF0Predictor.py
+++ /dev/null
@@ -1,86 +0,0 @@
-from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
-import pyworld
-import numpy as np
-
-
-class DioF0Predictor(F0Predictor):
-    def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sample_rate=44100):
-        self.hop_length = hop_length
-        self.f0_min = f0_min
-        self.f0_max = f0_max
-        self.sample_rate = sample_rate
-
-    def interpolate_f0(self, f0):
-        data = np.reshape(f0, (f0.size, 1))
-
-        vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
-        vuv_vector[data > 0.0] = 1.0
-        vuv_vector[data <= 0.0] = 0.0
-
-        ip_data = data
-
-        frame_number = data.size
-        last_value = 0.0
-        for i in range(frame_number):
-            if data[i] <= 0.0:
-                j = i + 1
-                for j in range(i + 1, frame_number):
-                    if data[j] > 0.0:
-                        break
-                if j < frame_number - 1:
-                    if last_value > 0.0:
-                        step = (data[j] - data[i - 1]) / float(j - i)
-                        for k in range(i, j):
-                            ip_data[k] = data[i - 1] + step * (k - i + 1)
-                    else:
-                        for k in range(i, j):
-                            ip_data[k] = data[j]
-                else:
-                    for k in range(i, frame_number):
-                        ip_data[k] = last_value
-            else:
-                ip_data[i] = data[i]  # 这里可能存在一个没有必要的拷贝
-                last_value = data[i]
-
-        return ip_data[:, 0], vuv_vector[:, 0]
-
-    def resize_f0(self, x, target_len):
-        source = np.array(x)
-        source[source < 0.001] = np.nan
-        target = np.interp(
-            np.arange(0, len(source) * target_len, len(source)) / target_len,
-            np.arange(0, len(source)),
-            source,
-        )
-        res = np.nan_to_num(target)
-        return res
-
-    def compute_f0(self, wav, p_len=None):
-        if p_len is None:
-            p_len = wav.shape[0] // self.hop_length
-        f0, t = pyworld.dio(
-            wav.astype(np.double),
-            fs=self.sample_rate,
-            f0_floor=self.f0_min,
-            f0_ceil=self.f0_max,
-            frame_period=1000 * self.hop_length / self.sample_rate,
-        )
-        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sample_rate)
-        for index, pitch in enumerate(f0):
-            f0[index] = round(pitch, 1)
-        return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
-
-    def compute_f0_uv(self, wav, p_len=None):
-        if p_len is None:
-            p_len = wav.shape[0] // self.hop_length
-        f0, t = pyworld.dio(
-            wav.astype(np.double),
-            fs=self.sample_rate,
-            f0_floor=self.f0_min,
-            f0_ceil=self.f0_max,
-            frame_period=1000 * self.hop_length / self.sample_rate,
-        )
-        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sample_rate)
-        for index, pitch in enumerate(f0):
-            f0[index] = round(pitch, 1)
-        return self.interpolate_f0(self.resize_f0(f0, p_len))
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/F0Predictor.py b/rvc/lib/infer_pack/modules/F0Predictor/F0Predictor.py
deleted file mode 100644
index 384f43f..0000000
--- a/rvc/lib/infer_pack/modules/F0Predictor/F0Predictor.py
+++ /dev/null
@@ -1,6 +0,0 @@
-class F0Predictor(object):
-    def compute_f0(self, wav, p_len):
-        pass
-
-    def compute_f0_uv(self, wav, p_len):
-        pass
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py b/rvc/lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py
deleted file mode 100644
index f30f61b..0000000
--- a/rvc/lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py
+++ /dev/null
@@ -1,82 +0,0 @@
-from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
-import pyworld
-import numpy as np
-
-
-class HarvestF0Predictor(F0Predictor):
-    def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sample_rate=44100):
-        self.hop_length = hop_length
-        self.f0_min = f0_min
-        self.f0_max = f0_max
-        self.sample_rate = sample_rate
-
-    def interpolate_f0(self, f0):
-        data = np.reshape(f0, (f0.size, 1))
-
-        vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
-        vuv_vector[data > 0.0] = 1.0
-        vuv_vector[data <= 0.0] = 0.0
-
-        ip_data = data
-
-        frame_number = data.size
-        last_value = 0.0
-        for i in range(frame_number):
-            if data[i] <= 0.0:
-                j = i + 1
-                for j in range(i + 1, frame_number):
-                    if data[j] > 0.0:
-                        break
-                if j < frame_number - 1:
-                    if last_value > 0.0:
-                        step = (data[j] - data[i - 1]) / float(j - i)
-                        for k in range(i, j):
-                            ip_data[k] = data[i - 1] + step * (k - i + 1)
-                    else:
-                        for k in range(i, j):
-                            ip_data[k] = data[j]
-                else:
-                    for k in range(i, frame_number):
-                        ip_data[k] = last_value
-            else:
-                ip_data[i] = data[i]
-                last_value = data[i]
-
-        return ip_data[:, 0], vuv_vector[:, 0]
-
-    def resize_f0(self, x, target_len):
-        source = np.array(x)
-        source[source < 0.001] = np.nan
-        target = np.interp(
-            np.arange(0, len(source) * target_len, len(source)) / target_len,
-            np.arange(0, len(source)),
-            source,
-        )
-        res = np.nan_to_num(target)
-        return res
-
-    def compute_f0(self, wav, p_len=None):
-        if p_len is None:
-            p_len = wav.shape[0] // self.hop_length
-        f0, t = pyworld.harvest(
-            wav.astype(np.double),
-            fs=self.sample_rate,
-            f0_ceil=self.f0_max,
-            f0_floor=self.f0_min,
-            frame_period=1000 * self.hop_length / self.sample_rate,
-        )
-        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.fs)
-        return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
-
-    def compute_f0_uv(self, wav, p_len=None):
-        if p_len is None:
-            p_len = wav.shape[0] // self.hop_length
-        f0, t = pyworld.harvest(
-            wav.astype(np.double),
-            fs=self.sample_rate,
-            f0_floor=self.f0_min,
-            f0_ceil=self.f0_max,
-            frame_period=1000 * self.hop_length / self.sample_rate,
-        )
-        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sample_rate)
-        return self.interpolate_f0(self.resize_f0(f0, p_len))
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/PMF0Predictor.py b/rvc/lib/infer_pack/modules/F0Predictor/PMF0Predictor.py
deleted file mode 100644
index 1b81a9f..0000000
--- a/rvc/lib/infer_pack/modules/F0Predictor/PMF0Predictor.py
+++ /dev/null
@@ -1,93 +0,0 @@
-from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
-import parselmouth
-import numpy as np
-
-
-class PMF0Predictor(F0Predictor):
-    def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sample_rate=44100):
-        self.hop_length = hop_length
-        self.f0_min = f0_min
-        self.f0_max = f0_max
-        self.sample_rate = sample_rate
-
-    def interpolate_f0(self, f0):
-        data = np.reshape(f0, (f0.size, 1))
-
-        vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
-        vuv_vector[data > 0.0] = 1.0
-        vuv_vector[data <= 0.0] = 0.0
-
-        ip_data = data
-
-        frame_number = data.size
-        last_value = 0.0
-        for i in range(frame_number):
-            if data[i] <= 0.0:
-                j = i + 1
-                for j in range(i + 1, frame_number):
-                    if data[j] > 0.0:
-                        break
-                if j < frame_number - 1:
-                    if last_value > 0.0:
-                        step = (data[j] - data[i - 1]) / float(j - i)
-                        for k in range(i, j):
-                            ip_data[k] = data[i - 1] + step * (k - i + 1)
-                    else:
-                        for k in range(i, j):
-                            ip_data[k] = data[j]
-                else:
-                    for k in range(i, frame_number):
-                        ip_data[k] = last_value
-            else:
-                ip_data[i] = data[i]  # 这里可能存在一个没有必要的拷贝
-                last_value = data[i]
-
-        return ip_data[:, 0], vuv_vector[:, 0]
-
-    def compute_f0(self, wav, p_len=None):
-        x = wav
-        if p_len is None:
-            p_len = x.shape[0] // self.hop_length
-        else:
-            assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
-        time_step = self.hop_length / self.sample_rate * 1000
-        f0 = (
-            parselmouth.Sound(x, self.sample_rate)
-            .to_pitch_ac(
-                time_step=time_step / 1000,
-                voicing_threshold=0.6,
-                pitch_floor=self.f0_min,
-                pitch_ceiling=self.f0_max,
-            )
-            .selected_array["frequency"]
-        )
-
-        pad_size = (p_len - len(f0) + 1) // 2
-        if pad_size > 0 or p_len - len(f0) - pad_size > 0:
-            f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
-        f0, uv = self.interpolate_f0(f0)
-        return f0
-
-    def compute_f0_uv(self, wav, p_len=None):
-        x = wav
-        if p_len is None:
-            p_len = x.shape[0] // self.hop_length
-        else:
-            assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
-        time_step = self.hop_length / self.sample_rate * 1000
-        f0 = (
-            parselmouth.Sound(x, self.sample_rate)
-            .to_pitch_ac(
-                time_step=time_step / 1000,
-                voicing_threshold=0.6,
-                pitch_floor=self.f0_min,
-                pitch_ceiling=self.f0_max,
-            )
-            .selected_array["frequency"]
-        )
-
-        pad_size = (p_len - len(f0) + 1) // 2
-        if pad_size > 0 or p_len - len(f0) - pad_size > 0:
-            f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
-        f0, uv = self.interpolate_f0(f0)
-        return f0, uv
diff --git a/rvc/lib/infer_pack/modules/F0Predictor/__init__.py b/rvc/lib/infer_pack/modules/F0Predictor/__init__.py
deleted file mode 100644
index e69de29..0000000
diff --git a/rvc/lib/infer_pack/transforms.py b/rvc/lib/infer_pack/transforms.py
deleted file mode 100644
index a11f799..0000000
--- a/rvc/lib/infer_pack/transforms.py
+++ /dev/null
@@ -1,209 +0,0 @@
-import torch
-from torch.nn import functional as F
-
-import numpy as np
-
-
-DEFAULT_MIN_BIN_WIDTH = 1e-3
-DEFAULT_MIN_BIN_HEIGHT = 1e-3
-DEFAULT_MIN_DERIVATIVE = 1e-3
-
-
-def piecewise_rational_quadratic_transform(
-    inputs,
-    unnormalized_widths,
-    unnormalized_heights,
-    unnormalized_derivatives,
-    inverse=False,
-    tails=None,
-    tail_bound=1.0,
-    min_bin_width=DEFAULT_MIN_BIN_WIDTH,
-    min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
-    min_derivative=DEFAULT_MIN_DERIVATIVE,
-):
-    if tails is None:
-        spline_fn = rational_quadratic_spline
-        spline_kwargs = {}
-    else:
-        spline_fn = unconstrained_rational_quadratic_spline
-        spline_kwargs = {"tails": tails, "tail_bound": tail_bound}
-
-    outputs, logabsdet = spline_fn(
-        inputs=inputs,
-        unnormalized_widths=unnormalized_widths,
-        unnormalized_heights=unnormalized_heights,
-        unnormalized_derivatives=unnormalized_derivatives,
-        inverse=inverse,
-        min_bin_width=min_bin_width,
-        min_bin_height=min_bin_height,
-        min_derivative=min_derivative,
-        **spline_kwargs
-    )
-    return outputs, logabsdet
-
-
-def searchsorted(bin_locations, inputs, eps=1e-6):
-    bin_locations[..., -1] += eps
-    return torch.sum(inputs[..., None] >= bin_locations, dim=-1) - 1
-
-
-def unconstrained_rational_quadratic_spline(
-    inputs,
-    unnormalized_widths,
-    unnormalized_heights,
-    unnormalized_derivatives,
-    inverse=False,
-    tails="linear",
-    tail_bound=1.0,
-    min_bin_width=DEFAULT_MIN_BIN_WIDTH,
-    min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
-    min_derivative=DEFAULT_MIN_DERIVATIVE,
-):
-    inside_interval_mask = (inputs >= -tail_bound) & (inputs <= tail_bound)
-    outside_interval_mask = ~inside_interval_mask
-
-    outputs = torch.zeros_like(inputs)
-    logabsdet = torch.zeros_like(inputs)
-
-    if tails == "linear":
-        unnormalized_derivatives = F.pad(unnormalized_derivatives, pad=(1, 1))
-        constant = np.log(np.exp(1 - min_derivative) - 1)
-        unnormalized_derivatives[..., 0] = constant
-        unnormalized_derivatives[..., -1] = constant
-
-        outputs[outside_interval_mask] = inputs[outside_interval_mask]
-        logabsdet[outside_interval_mask] = 0
-    else:
-        raise RuntimeError("{} tails are not implemented.".format(tails))
-
-    (
-        outputs[inside_interval_mask],
-        logabsdet[inside_interval_mask],
-    ) = rational_quadratic_spline(
-        inputs=inputs[inside_interval_mask],
-        unnormalized_widths=unnormalized_widths[inside_interval_mask, :],
-        unnormalized_heights=unnormalized_heights[inside_interval_mask, :],
-        unnormalized_derivatives=unnormalized_derivatives[inside_interval_mask, :],
-        inverse=inverse,
-        left=-tail_bound,
-        right=tail_bound,
-        bottom=-tail_bound,
-        top=tail_bound,
-        min_bin_width=min_bin_width,
-        min_bin_height=min_bin_height,
-        min_derivative=min_derivative,
-    )
-
-    return outputs, logabsdet
-
-
-def rational_quadratic_spline(
-    inputs,
-    unnormalized_widths,
-    unnormalized_heights,
-    unnormalized_derivatives,
-    inverse=False,
-    left=0.0,
-    right=1.0,
-    bottom=0.0,
-    top=1.0,
-    min_bin_width=DEFAULT_MIN_BIN_WIDTH,
-    min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
-    min_derivative=DEFAULT_MIN_DERIVATIVE,
-):
-    if torch.min(inputs) < left or torch.max(inputs) > right:
-        raise ValueError("Input to a transform is not within its domain")
-
-    num_bins = unnormalized_widths.shape[-1]
-
-    if min_bin_width * num_bins > 1.0:
-        raise ValueError("Minimal bin width too large for the number of bins")
-    if min_bin_height * num_bins > 1.0:
-        raise ValueError("Minimal bin height too large for the number of bins")
-
-    widths = F.softmax(unnormalized_widths, dim=-1)
-    widths = min_bin_width + (1 - min_bin_width * num_bins) * widths
-    cumwidths = torch.cumsum(widths, dim=-1)
-    cumwidths = F.pad(cumwidths, pad=(1, 0), mode="constant", value=0.0)
-    cumwidths = (right - left) * cumwidths + left
-    cumwidths[..., 0] = left
-    cumwidths[..., -1] = right
-    widths = cumwidths[..., 1:] - cumwidths[..., :-1]
-
-    derivatives = min_derivative + F.softplus(unnormalized_derivatives)
-
-    heights = F.softmax(unnormalized_heights, dim=-1)
-    heights = min_bin_height + (1 - min_bin_height * num_bins) * heights
-    cumheights = torch.cumsum(heights, dim=-1)
-    cumheights = F.pad(cumheights, pad=(1, 0), mode="constant", value=0.0)
-    cumheights = (top - bottom) * cumheights + bottom
-    cumheights[..., 0] = bottom
-    cumheights[..., -1] = top
-    heights = cumheights[..., 1:] - cumheights[..., :-1]
-
-    if inverse:
-        bin_idx = searchsorted(cumheights, inputs)[..., None]
-    else:
-        bin_idx = searchsorted(cumwidths, inputs)[..., None]
-
-    input_cumwidths = cumwidths.gather(-1, bin_idx)[..., 0]
-    input_bin_widths = widths.gather(-1, bin_idx)[..., 0]
-
-    input_cumheights = cumheights.gather(-1, bin_idx)[..., 0]
-    delta = heights / widths
-    input_delta = delta.gather(-1, bin_idx)[..., 0]
-
-    input_derivatives = derivatives.gather(-1, bin_idx)[..., 0]
-    input_derivatives_plus_one = derivatives[..., 1:].gather(-1, bin_idx)[..., 0]
-
-    input_heights = heights.gather(-1, bin_idx)[..., 0]
-
-    if inverse:
-        a = (inputs - input_cumheights) * (
-            input_derivatives + input_derivatives_plus_one - 2 * input_delta
-        ) + input_heights * (input_delta - input_derivatives)
-        b = input_heights * input_derivatives - (inputs - input_cumheights) * (
-            input_derivatives + input_derivatives_plus_one - 2 * input_delta
-        )
-        c = -input_delta * (inputs - input_cumheights)
-
-        discriminant = b.pow(2) - 4 * a * c
-        assert (discriminant >= 0).all()
-
-        root = (2 * c) / (-b - torch.sqrt(discriminant))
-        outputs = root * input_bin_widths + input_cumwidths
-
-        theta_one_minus_theta = root * (1 - root)
-        denominator = input_delta + (
-            (input_derivatives + input_derivatives_plus_one - 2 * input_delta)
-            * theta_one_minus_theta
-        )
-        derivative_numerator = input_delta.pow(2) * (
-            input_derivatives_plus_one * root.pow(2)
-            + 2 * input_delta * theta_one_minus_theta
-            + input_derivatives * (1 - root).pow(2)
-        )
-        logabsdet = torch.log(derivative_numerator) - 2 * torch.log(denominator)
-
-        return outputs, -logabsdet
-    else:
-        theta = (inputs - input_cumwidths) / input_bin_widths
-        theta_one_minus_theta = theta * (1 - theta)
-
-        numerator = input_heights * (
-            input_delta * theta.pow(2) + input_derivatives * theta_one_minus_theta
-        )
-        denominator = input_delta + (
-            (input_derivatives + input_derivatives_plus_one - 2 * input_delta)
-            * theta_one_minus_theta
-        )
-        outputs = input_cumheights + numerator / denominator
-
-        derivative_numerator = input_delta.pow(2) * (
-            input_derivatives_plus_one * theta.pow(2)
-            + 2 * input_delta * theta_one_minus_theta
-            + input_derivatives * (1 - theta).pow(2)
-        )
-        logabsdet = torch.log(derivative_numerator) - 2 * torch.log(denominator)
-
-        return outputs, logabsdet
diff --git a/rvc/lib/rmvpe.py b/rvc/lib/rmvpe.py
deleted file mode 100644
index 89b984b..0000000
--- a/rvc/lib/rmvpe.py
+++ /dev/null
@@ -1,388 +0,0 @@
-import torch.nn as nn
-import torch, numpy as np
-import torch.nn.functional as F
-from librosa.filters import mel
-
-
-class BiGRU(nn.Module):
-    def __init__(self, input_features, hidden_features, num_layers):
-        super(BiGRU, self).__init__()
-        self.gru = nn.GRU(
-            input_features,
-            hidden_features,
-            num_layers=num_layers,
-            batch_first=True,
-            bidirectional=True,
-        )
-
-    def forward(self, x):
-        return self.gru(x)[0]
-
-
-class ConvBlockRes(nn.Module):
-    def __init__(self, in_channels, out_channels, momentum=0.01):
-        super(ConvBlockRes, self).__init__()
-        self.conv = nn.Sequential(
-            nn.Conv2d(
-                in_channels=in_channels,
-                out_channels=out_channels,
-                kernel_size=(3, 3),
-                stride=(1, 1),
-                padding=(1, 1),
-                bias=False,
-            ),
-            nn.BatchNorm2d(out_channels, momentum=momentum),
-            nn.ReLU(),
-            nn.Conv2d(
-                in_channels=out_channels,
-                out_channels=out_channels,
-                kernel_size=(3, 3),
-                stride=(1, 1),
-                padding=(1, 1),
-                bias=False,
-            ),
-            nn.BatchNorm2d(out_channels, momentum=momentum),
-            nn.ReLU(),
-        )
-        if in_channels != out_channels:
-            self.shortcut = nn.Conv2d(in_channels, out_channels, (1, 1))
-            self.is_shortcut = True
-        else:
-            self.is_shortcut = False
-
-    def forward(self, x):
-        if self.is_shortcut:
-            return self.conv(x) + self.shortcut(x)
-        else:
-            return self.conv(x) + x
-
-
-class Encoder(nn.Module):
-    def __init__(
-        self,
-        in_channels,
-        in_size,
-        n_encoders,
-        kernel_size,
-        n_blocks,
-        out_channels=16,
-        momentum=0.01,
-    ):
-        super(Encoder, self).__init__()
-        self.n_encoders = n_encoders
-        self.bn = nn.BatchNorm2d(in_channels, momentum=momentum)
-        self.layers = nn.ModuleList()
-        self.latent_channels = []
-        for i in range(self.n_encoders):
-            self.layers.append(
-                ResEncoderBlock(
-                    in_channels, out_channels, kernel_size, n_blocks, momentum=momentum
-                )
-            )
-            self.latent_channels.append([out_channels, in_size])
-            in_channels = out_channels
-            out_channels *= 2
-            in_size //= 2
-        self.out_size = in_size
-        self.out_channel = out_channels
-
-    def forward(self, x):
-        concat_tensors = []
-        x = self.bn(x)
-        for i in range(self.n_encoders):
-            _, x = self.layers[i](x)
-            concat_tensors.append(_)
-        return x, concat_tensors
-
-
-class ResEncoderBlock(nn.Module):
-    def __init__(
-        self, in_channels, out_channels, kernel_size, n_blocks=1, momentum=0.01
-    ):
-        super(ResEncoderBlock, self).__init__()
-        self.n_blocks = n_blocks
-        self.conv = nn.ModuleList()
-        self.conv.append(ConvBlockRes(in_channels, out_channels, momentum))
-        for i in range(n_blocks - 1):
-            self.conv.append(ConvBlockRes(out_channels, out_channels, momentum))
-        self.kernel_size = kernel_size
-        if self.kernel_size is not None:
-            self.pool = nn.AvgPool2d(kernel_size=kernel_size)
-
-    def forward(self, x):
-        for i in range(self.n_blocks):
-            x = self.conv[i](x)
-        if self.kernel_size is not None:
-            return x, self.pool(x)
-        else:
-            return x
-
-
-class Intermediate(nn.Module):  #
-    def __init__(self, in_channels, out_channels, n_inters, n_blocks, momentum=0.01):
-        super(Intermediate, self).__init__()
-        self.n_inters = n_inters
-        self.layers = nn.ModuleList()
-        self.layers.append(
-            ResEncoderBlock(in_channels, out_channels, None, n_blocks, momentum)
-        )
-        for i in range(self.n_inters - 1):
-            self.layers.append(
-                ResEncoderBlock(out_channels, out_channels, None, n_blocks, momentum)
-            )
-
-    def forward(self, x):
-        for i in range(self.n_inters):
-            x = self.layers[i](x)
-        return x
-
-
-class ResDecoderBlock(nn.Module):
-    def __init__(self, in_channels, out_channels, stride, n_blocks=1, momentum=0.01):
-        super(ResDecoderBlock, self).__init__()
-        out_padding = (0, 1) if stride == (1, 2) else (1, 1)
-        self.n_blocks = n_blocks
-        self.conv1 = nn.Sequential(
-            nn.ConvTranspose2d(
-                in_channels=in_channels,
-                out_channels=out_channels,
-                kernel_size=(3, 3),
-                stride=stride,
-                padding=(1, 1),
-                output_padding=out_padding,
-                bias=False,
-            ),
-            nn.BatchNorm2d(out_channels, momentum=momentum),
-            nn.ReLU(),
-        )
-        self.conv2 = nn.ModuleList()
-        self.conv2.append(ConvBlockRes(out_channels * 2, out_channels, momentum))
-        for i in range(n_blocks - 1):
-            self.conv2.append(ConvBlockRes(out_channels, out_channels, momentum))
-
-    def forward(self, x, concat_tensor):
-        x = self.conv1(x)
-        x = torch.cat((x, concat_tensor), dim=1)
-        for i in range(self.n_blocks):
-            x = self.conv2[i](x)
-        return x
-
-
-class Decoder(nn.Module):
-    def __init__(self, in_channels, n_decoders, stride, n_blocks, momentum=0.01):
-        super(Decoder, self).__init__()
-        self.layers = nn.ModuleList()
-        self.n_decoders = n_decoders
-        for i in range(self.n_decoders):
-            out_channels = in_channels // 2
-            self.layers.append(
-                ResDecoderBlock(in_channels, out_channels, stride, n_blocks, momentum)
-            )
-            in_channels = out_channels
-
-    def forward(self, x, concat_tensors):
-        for i in range(self.n_decoders):
-            x = self.layers[i](x, concat_tensors[-1 - i])
-        return x
-
-
-class DeepUnet(nn.Module):
-    def __init__(
-        self,
-        kernel_size,
-        n_blocks,
-        en_de_layers=5,
-        inter_layers=4,
-        in_channels=1,
-        en_out_channels=16,
-    ):
-        super(DeepUnet, self).__init__()
-        self.encoder = Encoder(
-            in_channels, 128, en_de_layers, kernel_size, n_blocks, en_out_channels
-        )
-        self.intermediate = Intermediate(
-            self.encoder.out_channel // 2,
-            self.encoder.out_channel,
-            inter_layers,
-            n_blocks,
-        )
-        self.decoder = Decoder(
-            self.encoder.out_channel, en_de_layers, kernel_size, n_blocks
-        )
-
-    def forward(self, x):
-        x, concat_tensors = self.encoder(x)
-        x = self.intermediate(x)
-        x = self.decoder(x, concat_tensors)
-        return x
-
-
-class E2E(nn.Module):
-    def __init__(
-        self,
-        n_blocks,
-        n_gru,
-        kernel_size,
-        en_de_layers=5,
-        inter_layers=4,
-        in_channels=1,
-        en_out_channels=16,
-    ):
-        super(E2E, self).__init__()
-        self.unet = DeepUnet(
-            kernel_size,
-            n_blocks,
-            en_de_layers,
-            inter_layers,
-            in_channels,
-            en_out_channels,
-        )
-        self.cnn = nn.Conv2d(en_out_channels, 3, (3, 3), padding=(1, 1))
-        if n_gru:
-            self.fc = nn.Sequential(
-                BiGRU(3 * 128, 256, n_gru),
-                nn.Linear(512, 360),
-                nn.Dropout(0.25),
-                nn.Sigmoid(),
-            )
-
-    def forward(self, mel):
-        mel = mel.transpose(-1, -2).unsqueeze(1)
-        x = self.cnn(self.unet(mel)).transpose(1, 2).flatten(-2)
-        x = self.fc(x)
-        return x
-
-
-class MelSpectrogram(torch.nn.Module):
-    def __init__(
-        self,
-        is_half,
-        n_mel_channels,
-        sample_rate,
-        win_length,
-        hop_length,
-        n_fft=None,
-        mel_fmin=0,
-        mel_fmax=None,
-        clamp=1e-5,
-    ):
-        super().__init__()
-        n_fft = win_length if n_fft is None else n_fft
-        self.hann_window = {}
-        mel_basis = mel(
-            sr=sample_rate,
-            n_fft=n_fft,
-            n_mels=n_mel_channels,
-            fmin=mel_fmin,
-            fmax=mel_fmax,
-            htk=True,
-        )
-        mel_basis = torch.from_numpy(mel_basis).float()
-        self.register_buffer("mel_basis", mel_basis)
-        self.n_fft = win_length if n_fft is None else n_fft
-        self.hop_length = hop_length
-        self.win_length = win_length
-        self.sample_rate = sample_rate
-        self.n_mel_channels = n_mel_channels
-        self.clamp = clamp
-        self.is_half = is_half
-
-    def forward(self, audio, keyshift=0, speed=1, center=True):
-        factor = 2 ** (keyshift / 12)
-        n_fft_new = int(np.round(self.n_fft * factor))
-        win_length_new = int(np.round(self.win_length * factor))
-        hop_length_new = int(np.round(self.hop_length * speed))
-        keyshift_key = str(keyshift) + "_" + str(audio.device)
-        if keyshift_key not in self.hann_window:
-            self.hann_window[keyshift_key] = torch.hann_window(win_length_new).to(
-                audio.device
-            )
-        fft = torch.stft(
-            audio,
-            n_fft=n_fft_new,
-            hop_length=hop_length_new,
-            win_length=win_length_new,
-            window=self.hann_window[keyshift_key],
-            center=center,
-            return_complex=True,
-        )
-        magnitude = torch.sqrt(fft.real.pow(2) + fft.imag.pow(2))
-        if keyshift != 0:
-            size = self.n_fft // 2 + 1
-            resize = magnitude.size(1)
-            if resize < size:
-                magnitude = F.pad(magnitude, (0, 0, 0, size - resize))
-            magnitude = magnitude[:, :size, :] * self.win_length / win_length_new
-        mel_output = torch.matmul(self.mel_basis, magnitude)
-        if self.is_half == True:
-            mel_output = mel_output.half()
-        log_mel_spec = torch.log(torch.clamp(mel_output, min=self.clamp))
-        return log_mel_spec
-
-
-class RMVPE:
-    def __init__(self, model_path, is_half, device=None):
-        self.resample_kernel = {}
-        model = E2E(4, 1, (2, 2))
-        ckpt = torch.load(model_path, map_location="cpu")
-        model.load_state_dict(ckpt)
-        model.eval()
-        if is_half == True:
-            model = model.half()
-        self.model = model
-        self.resample_kernel = {}
-        self.is_half = is_half
-        if device is None:
-            device = "cuda" if torch.cuda.is_available() else "cpu"
-        self.device = device
-        self.mel_extractor = MelSpectrogram(
-            is_half, 128, 16000, 1024, 160, None, 30, 8000
-        ).to(device)
-        self.model = self.model.to(device)
-        cents_mapping = 20 * np.arange(360) + 1997.3794084376191
-        self.cents_mapping = np.pad(cents_mapping, (4, 4))  # 368
-
-    def mel2hidden(self, mel):
-        with torch.no_grad():
-            n_frames = mel.shape[-1]
-            mel = F.pad(
-                mel, (0, 32 * ((n_frames - 1) // 32 + 1) - n_frames), mode="reflect"
-            )
-            hidden = self.model(mel)
-            return hidden[:, :n_frames]
-
-    def decode(self, hidden, thred=0.03):
-        cents_pred = self.to_local_average_cents(hidden, thred=thred)
-        f0 = 10 * (2 ** (cents_pred / 1200))
-        f0[f0 == 10] = 0
-        return f0
-
-    def infer_from_audio(self, audio, thred=0.03):
-        audio = torch.from_numpy(audio).float().to(self.device).unsqueeze(0)
-        mel = self.mel_extractor(audio, center=True)
-        hidden = self.mel2hidden(mel)
-        hidden = hidden.squeeze(0).cpu().numpy()
-        if self.is_half == True:
-            hidden = hidden.astype("float32")
-        f0 = self.decode(hidden, thred=thred)
-        return f0
-
-    def to_local_average_cents(self, salience, thred=0.05):
-        center = np.argmax(salience, axis=1)
-        salience = np.pad(salience, ((0, 0), (4, 4)))
-        center += 4
-        todo_salience = []
-        todo_cents_mapping = []
-        starts = center - 4
-        ends = center + 5
-        for idx in range(salience.shape[0]):
-            todo_salience.append(salience[:, starts[idx] : ends[idx]][idx])
-            todo_cents_mapping.append(self.cents_mapping[starts[idx] : ends[idx]])
-        todo_salience = np.array(todo_salience)
-        todo_cents_mapping = np.array(todo_cents_mapping)
-        product_sum = np.sum(todo_salience * todo_cents_mapping, 1)
-        weight_sum = np.sum(todo_salience, 1)
-        devided = product_sum / weight_sum
-        maxx = np.max(salience, axis=1)
-        devided[maxx <= thred] = 0
-        return devided
diff --git a/rvc/pretraineds/.gitignore b/rvc/pretraineds/.gitignore
deleted file mode 100644
index e69de29..0000000
diff --git a/rvc/pretraineds/pretrained_v1/.gitignore b/rvc/pretraineds/pretrained_v1/.gitignore
deleted file mode 100644
index e69de29..0000000
diff --git a/rvc/pretraineds/pretrained_v2/.gitignore b/rvc/pretraineds/pretrained_v2/.gitignore
deleted file mode 100644
index e69de29..0000000