Pinned Loading

1. FunAudioLLM/CosyVoice FunAudioLLM/CosyVoice Public

   Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

   Python 12.3k 1.2k

2. modelscope/FunASR modelscope/FunASR Public

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

   Python 9.1k 926

3. modelscope/FunCodec modelscope/FunCodec Public

   FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.

   Python 392 33