search

FunAudioLLM / CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
https://funaudiollm.github.io/
Apache License 2.0
4.66k stars 471 forks source link

Extracting spk embedding is too slow #229

Open WangGewu opened 1 month ago

WangGewu commented 1 month ago

可以提供campplus的pt文件和batch推理代码吗？目前使用campplus.onnx提取spk embedding，速度太慢。

aluminumbox commented 1 month ago

well we may consider it later as many people have raised this problem

WoBuChiTang commented 1 month ago

well we may consider it later as many people have raised this problem

是的确实有点慢，希望至少提速到和speech2token差不多的速度

Wentao795 commented 1 month ago

+1，

huskyachao commented 1 month ago

+1 :）

github-actions[bot] commented 4 days ago

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