🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Speech recognition module for Python, supporting several engines and APIs, online and offline.

End-to-End Speech Processing Toolkit

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

Machine Learning Resources, Practice and Research

A PyTorch-based Speech Toolkit

Faster Whisper transcription with CTranslate2

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Production First and Production Ready End-to-End Speech Recognition Toolkit

All-in-One Development Tool based on PaddlePaddle

Your Own Personal Voice Assistant. It's a mini python project.

Multilingual Voice Understanding Model

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks

Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.

On-device wake word detection powered by deep learning

OpenAI Whisper ASR Webservice API

End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

中文语音识别; Mandarin Automatic Speech Recognition;