├── Baichuan-Audio.pdf ├── LICENSE ├── NOTICE ├── README.md ├── README_zh.md ├── assets ├── audio_out.wav ├── audiollm.png ├── data.png ├── decoder.png ├── logo.png ├── result.png ├── table.png └── vq.png ├── requirements.txt ├── third_party └── cosy24k_vocoder │ ├── LICENSE │ ├── README.md │ ├── cosy24k_vocoder.py │ ├── hifigan │ ├── __init__.py │ ├── discriminator.py │ ├── f0_predictor.py │ ├── generator.py │ └── hifigan.py │ └── hift.pt └── web_demo ├── base_asr_demo.py ├── base_tts_demo.py ├── constants.py ├── data ├── 1497.wav ├── 1889.wav ├── base_asr_example.jsonl └── base_tts_example.jsonl ├── generation.py └── s2s_gradio_demo_cosy_multiturn.py /Baichuan-Audio.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/Baichuan-Audio.pdf -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/LICENSE -------------------------------------------------------------------------------- /NOTICE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/NOTICE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/README.md -------------------------------------------------------------------------------- /README_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/README_zh.md -------------------------------------------------------------------------------- /assets/audio_out.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/assets/audio_out.wav -------------------------------------------------------------------------------- /assets/audiollm.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/assets/audiollm.png -------------------------------------------------------------------------------- /assets/data.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/assets/data.png -------------------------------------------------------------------------------- /assets/decoder.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/assets/decoder.png -------------------------------------------------------------------------------- /assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/assets/logo.png -------------------------------------------------------------------------------- /assets/result.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/assets/result.png -------------------------------------------------------------------------------- /assets/table.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/assets/table.png -------------------------------------------------------------------------------- /assets/vq.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/assets/vq.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/requirements.txt -------------------------------------------------------------------------------- /third_party/cosy24k_vocoder/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/third_party/cosy24k_vocoder/LICENSE -------------------------------------------------------------------------------- /third_party/cosy24k_vocoder/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/third_party/cosy24k_vocoder/README.md -------------------------------------------------------------------------------- /third_party/cosy24k_vocoder/cosy24k_vocoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/third_party/cosy24k_vocoder/cosy24k_vocoder.py -------------------------------------------------------------------------------- /third_party/cosy24k_vocoder/hifigan/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/third_party/cosy24k_vocoder/hifigan/__init__.py -------------------------------------------------------------------------------- /third_party/cosy24k_vocoder/hifigan/discriminator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/third_party/cosy24k_vocoder/hifigan/discriminator.py -------------------------------------------------------------------------------- /third_party/cosy24k_vocoder/hifigan/f0_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/third_party/cosy24k_vocoder/hifigan/f0_predictor.py -------------------------------------------------------------------------------- /third_party/cosy24k_vocoder/hifigan/generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/third_party/cosy24k_vocoder/hifigan/generator.py -------------------------------------------------------------------------------- /third_party/cosy24k_vocoder/hifigan/hifigan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/third_party/cosy24k_vocoder/hifigan/hifigan.py -------------------------------------------------------------------------------- /third_party/cosy24k_vocoder/hift.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/third_party/cosy24k_vocoder/hift.pt -------------------------------------------------------------------------------- /web_demo/base_asr_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/web_demo/base_asr_demo.py -------------------------------------------------------------------------------- /web_demo/base_tts_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/web_demo/base_tts_demo.py -------------------------------------------------------------------------------- /web_demo/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/web_demo/constants.py -------------------------------------------------------------------------------- /web_demo/data/1497.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/web_demo/data/1497.wav -------------------------------------------------------------------------------- /web_demo/data/1889.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/web_demo/data/1889.wav -------------------------------------------------------------------------------- /web_demo/data/base_asr_example.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/web_demo/data/base_asr_example.jsonl -------------------------------------------------------------------------------- /web_demo/data/base_tts_example.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/web_demo/data/base_tts_example.jsonl -------------------------------------------------------------------------------- /web_demo/generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/web_demo/generation.py -------------------------------------------------------------------------------- /web_demo/s2s_gradio_demo_cosy_multiturn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/baichuan-inc/Baichuan-Audio/HEAD/web_demo/s2s_gradio_demo_cosy_multiturn.py --------------------------------------------------------------------------------