Libraries & frameworks
speechbrain
speechbrain/speechbrain
A PyTorch speech toolkit with recipes and pretrained models for recognition, enhancement, separation, and spoken language tasks.
Topics
Related projects
speech_recognition9kSpeechRecognition is a Python library that wraps many online and offline speech-to-text engines, including Google, Whisper and Vosk, for use in developers' own programs.
SALMONN1.6kByteDance's family of multimodal large language models for speech, audio and audio-visual understanding, released with model checkpoints and inference and training code.
faster-whisper26.7kA fast Whisper transcription library built on CTranslate2, with quantization, batching, VAD filtering, and word timestamps.
vosk-api15.2kAn offline speech recognition toolkit with small models and bindings for many languages, built for apps and devices.
audio3kTorchAudio, PyTorch's official library for loading audio datasets and applying transforms such as spectrograms, MFCC, and resampling in machine learning pipelines.
mlt1.9kAn LGPL multimedia framework designed for video editing. It provides the decoding, compositing, filtering, and timeline plumbing that editing applications build on.