FunAudioLLM / CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
https://funaudiollm.github.io/
Apache License 2.0
5.96k stars 637 forks source link

Inference code in c/++. #242

Open jerrypcl opened 2 months ago

jerrypcl commented 2 months ago

Is your feature request related to a problem? Please describe. A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] We need integrate in c++ environment. Describe the solution you'd like A clear and concise description of what you want to happen. Less dependency on other modules is better. Just like k2 Sherpa, call PyTorch c api. If not, Wenet c++ style decoding is good too. Describe alternatives you've considered A clear and concise description of any alternative solutions or features you've considered. Calling Nvidia library directly to make it fast is good try too. Additional context Add any other context or screenshots about the feature request here. Thank you!

aluminumbox commented 2 months ago

we have no plan to do it yet, one reason is we are very busy, another is that this model is relatively complicated to export libtorch or onnx model, especially flow matching part

github-actions[bot] commented 1 month ago

This issue is stale because it has been open for 30 days with no activity.