transformers/docs/source/en/main_classes/feature_extractor.md

Feature Extractor

A feature extractor is in charge of preparing input features for audio or vision models. This includes feature extraction from sequences, e.g., pre-processing audio files to generate Log-Mel Spectrogram features, feature extraction from images, e.g., cropping image files, but also padding, normalization, and conversion to NumPy, PyTorch, and TensorFlow tensors.

FeatureExtractionMixin

[[autodoc]] feature_extraction_utils.FeatureExtractionMixin - from_pretrained - save_pretrained

SequenceFeatureExtractor

[[autodoc]] SequenceFeatureExtractor - pad

BatchFeature

[[autodoc]] BatchFeature

ImageFeatureExtractionMixin

[[autodoc]] image_utils.ImageFeatureExtractionMixin