convert-ckpt-to-ggml.py : error

[raphael10-collab]

As described here: ggerganov/llama.cpp#11242 ,
I want to convert this https://huggingface.co/speechbrain/asr-whisper-medium-commonvoice-it ckpt model to ggml :

Downloaded the model:

(.venv) raphy@raohy:~/whisper.cpp/models$ cat download-asr-w-medium-commonvoice-it.py
from huggingface_hub import snapshot_download
model_id="speechbrain/asr-whisper-medium-commonvoice-it"
snapshot_download(repo_id=model_id, local_dir="asr-w-medium-commonvoice-it",
                  local_dir_use_symlinks=False, revision="main")



(.venv) raphy@raohy:~/whisper.cpp/models$ python3 download-asr-w-medium-commonvoice-it.py
/home/raphy/whisper.cpp/models/.venv/lib/python3.12/site-packages/huggingface_hub/file_download.py:832: UserWarning: `local_dir_use_symlinks` parameter is deprecated and will be ignored. The process to download files to a local folder has been updated and do not rely on symlinks anymore. You only need to pass a destination folder as`local_dir`.
For more details, check out https://huggingface.co/docs/huggingface_hub/main/en/guides/download#download-files-to-local-folder.
  warnings.warn(
example-it.wav: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 136k/136k [00:00<00:00, 1.35MB/s]
config.json: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 43.0/43.0 [00:00<00:00, 133kB/s]
hyperparams.yaml: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.58k/1.58k [00:00<00:00, 8.58MB/s]
.gitattributes: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.52k/1.52k [00:00<00:00, 9.23MB/s]
README.md: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4.51k/4.51k [00:00<00:00, 17.3MB/s]
whisper.ckpt: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3.06G/3.06G [00:54<00:00, 56.4MB/s]
Fetching 6 files: 100%|█

Downloaded convert-ckpt-to-ggml.py from :

https://github.com/ggerganov/ggml/blob/master/examples/gpt-2/convert-ckpt-to-ggml.py

And tried to convert the file , but got FileNotFoundError: [Errno 2] No such file or directory: './encoder.json' error :

(.venv) raphy@raohy:~/whisper.cpp/models/asr-w-medium-commonvoice-it$ python3 ../llama.cpp/convert-ckpt-to-ggml.py . --outfile asr-w-medium-commonvoice-it.ggml --outtype f16
2025-01-14 17:32:46.776224: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1736872366.881500   48970 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1736872366.910231   48970 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2025-01-14 17:32:47.152768: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
  File "/home/raphy/whisper.cpp/models/asr-w-medium-commonvoice-it/../llama.cpp/convert-ckpt-to-ggml.py", line 66, in <module>
    with open(dir_model + "/encoder.json", "r", encoding="utf-8") as f:
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: './encoder.json'

How to make it work?