Fangjun Kuang
Fangjun Kuang
> Please see our icefall doc. Please see this comment. You need to spend some time reading our doc https://k2-fsa.github.io/icefall/
> but it seems that it's not specifically about creating voice dataset files for wenetspeech-kws Are there any differences between the dataset you want to build with other dataset examples...
1. Please create 3 text files. (a) wav.scp It should contain something like below ``` unique_id_1 /path/to/foo.wav unique_id_2 /path/to/bar.wav unique_id_3 /path/to/foobar.wav ``` (b) wav.scp It should contain something like below...
> Is there documentation on what CUDA toolkits are compatile with each version of sherpa-onnx? It depends on which version of onnxruntime you are using. We have been using onnxruntime...
You need to set model config debug to true and print all recognizer config to get help.
可以的。
> 就是 识别到的每一句话 在原始音频中的时间,数据 我也想要,应该怎么设置? https://k2-fsa.github.io/sherpa/onnx/sense-voice/python-api.html#generate-subtitles 这里有现成的例子. --- https://huggingface.co/spaces/k2-fsa/generate-subtitles-for-videos 可以在线体验
请看 https://github.com/FunAudioLLM/SenseVoice/issues/72#issuecomment-2883278099
请看 https://github.com/FunAudioLLM/SenseVoice/issues/72#issuecomment-2883278099
Could you show the output of ``` make VERBOSE=1 -j1 ```