GrouseY

$python audioAnalysis.py speakerDiarization -i ../your/data/file/dic/test.wav --num 0 --flsd and just in case you wanna generate segmented wav file, add the following after line 943 in audioSegmentation.py: (segs, classes) = flags2segs(cls,...

I've tested, with source in Chinese and target in English. The output quality is good, but since the model is trained with English, all the Chinese words will be pronounced...

I have the same issue and I fixed it by wget the model link again in the model directory. seems like git clone wouldn't download the whole model.