deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 09:29:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

add roadmap

Browse Source
This commit is contained in:
lyuxiang.lx
2024-07-30 13:51:20 +08:00
parent 2895d99b9a
commit 553244b8f2
1 changed files with 30 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
README.md
View File

@@ -4,6 +4,36 @@
For `SenseVoice`, visit [SenseVoice repo](https://github.com/FunAudioLLM/SenseVoice) and [SenseVoice space](https://www.modelscope.cn/studios/iic/SenseVoice). For `SenseVoice`, visit [SenseVoice repo](https://github.com/FunAudioLLM/SenseVoice) and [SenseVoice space](https://www.modelscope.cn/studios/iic/SenseVoice).
## Roadmap
- [x] 2024/07
- [x] Flow matching training support
- [x] WeTextProcessing support when ttsfrd is not avaliable
- [x] Fastapi server and client
- [ ] 2024/08
- [ ] Repetition Aware Sampling(RAS) inference for llm stability
- [ ] Streaming inference mode support, including kv cache and sdpa for rtf optimization
- [ ] 2024/09
- [ ] 50hz llm model which supports 10 language
- [ ] 2024/10
- [ ] 50hz llama based llm model which supports lora finetune
- [ ] TBD
- [ ] Support more instruction mode
- [ ] Voice conversion
- [ ] Music generation
- [ ] Training script sample based on Mandarin
- [ ] CosyVoice-500M trained with more multi-lingual data
- [ ] More...
## Install ## Install
**Clone and install** **Clone and install**