diff --git a/docs/api-inference/tasks/audio_classification.md b/docs/api-inference/tasks/audio_classification.md index b4be60e6a..78aacebd3 100644 --- a/docs/api-inference/tasks/audio_classification.md +++ b/docs/api-inference/tasks/audio_classification.md @@ -1,3 +1,17 @@ + + ## Audio Classification Audio classification is the task of assigning a label or class to a given audio. It can be used for recognizing which command a user is giving or the emotion of a statement, as well as identifying a speaker. diff --git a/docs/api-inference/tasks/automatic_speech_recognition.md b/docs/api-inference/tasks/automatic_speech_recognition.md index ae84ed195..1362e0ccc 100644 --- a/docs/api-inference/tasks/automatic_speech_recognition.md +++ b/docs/api-inference/tasks/automatic_speech_recognition.md @@ -1,3 +1,17 @@ + + ## Automatic Speech Recognition Automatic Speech Recognition (ASR), also known as Speech to Text (STT), is the task of transcribing a given audio to text. It has many applications, such as voice user interfaces. diff --git a/docs/api-inference/tasks/feature_extraction.md b/docs/api-inference/tasks/feature_extraction.md index 76e61ca08..0d2f46dcf 100644 --- a/docs/api-inference/tasks/feature_extraction.md +++ b/docs/api-inference/tasks/feature_extraction.md @@ -1,3 +1,17 @@ + + ## Feature Extraction Feature extraction is the task of converting a text into a vector (often called "embedding"). diff --git a/docs/api-inference/tasks/image_classification.md b/docs/api-inference/tasks/image_classification.md index 0825ce381..7060c35a8 100644 --- a/docs/api-inference/tasks/image_classification.md +++ b/docs/api-inference/tasks/image_classification.md @@ -1,3 +1,17 @@ + + ## Image Classification Image classification is the task of assigning a label or class to an entire image. Images are expected to have only one class for each image. Image classification models take an image as input and return a prediction about which class the image belongs to. diff --git a/docs/api-inference/tasks/image_segmentation.md b/docs/api-inference/tasks/image_segmentation.md index eb4dfd506..c88e29655 100644 --- a/docs/api-inference/tasks/image_segmentation.md +++ b/docs/api-inference/tasks/image_segmentation.md @@ -1,3 +1,17 @@ + + ## Image Segmentation Image Segmentation divides an image into segments where each pixel in the image is mapped to an object. This task has multiple variants such as instance segmentation, panoptic segmentation and semantic segmentation. diff --git a/docs/api-inference/tasks/object_detection.md b/docs/api-inference/tasks/object_detection.md index 6c83e973f..76b9dbcc5 100644 --- a/docs/api-inference/tasks/object_detection.md +++ b/docs/api-inference/tasks/object_detection.md @@ -1,3 +1,17 @@ + + ## Object detection Object Detection models allow users to identify objects of certain defined classes. Object detection models receive an image as input and output the images with bounding boxes and labels on detected objects. diff --git a/docs/api-inference/tasks/token_classification.md b/docs/api-inference/tasks/token_classification.md index df34ab08b..1113cf39e 100644 --- a/docs/api-inference/tasks/token_classification.md +++ b/docs/api-inference/tasks/token_classification.md @@ -1,3 +1,17 @@ + + ## Token Classification Token classification is a task in which a label is assigned to some tokens in a text. Some popular token classification subtasks are Named Entity Recognition (NER) and Part-of-Speech (PoS) tagging. diff --git a/docs/api-inference/tasks/translation.md b/docs/api-inference/tasks/translation.md index b92c0abe6..c924a8bd0 100644 --- a/docs/api-inference/tasks/translation.md +++ b/docs/api-inference/tasks/translation.md @@ -1,3 +1,17 @@ + + ## Translation Translation is the task of converting text from one language to another. diff --git a/docs/api-inference/tasks/zero_shot_classification.md b/docs/api-inference/tasks/zero_shot_classification.md index 7460ddbdd..0c2f4dfa9 100644 --- a/docs/api-inference/tasks/zero_shot_classification.md +++ b/docs/api-inference/tasks/zero_shot_classification.md @@ -1,3 +1,17 @@ + + ## Zero-Shot Classification Zero-shot text classification is super useful to try out classification with zero code, you simply pass a sentence/paragraph and the possible labels for that sentence, and you get a result. The model has not been necessarily trained on the labels you provide, but it can still predict the correct label.