fangruyu

Where are the JSON files for the training and testing sets in the data section of exp/unet16.json

Why is the audio unchanged after separation?

8

Run successfully： INFO:spleeter:File audio_output/Split_1/vocals.wav written succesfully INFO:spleeter:File audio_output/Split_1/accompaniment.wav written succesfully but vocals.wav and accompaniment.wav are the same as original audio, no change

fMLLR transforms failed. report: Failed to read vector from stream. Error reading vector data (binary mode); truncated stream? (size = 38) File position at start is -1, currently -1

2

When I use the corpus (wenetspeech) to train the chain model, an error occurs when I reach the steps/align_fmllr.sh step: ``` run.pl: 1 / 25 failed, log is in exp/tri5a_sp_ali/log/fmllr.*.log...

现在能下到的版本和你代码里的不兼容，配置文件对不上，大佬可否共享一下之前旧版的模型文件？ 如果可以的话，可以发我邮箱吗？[email protected]。万分感谢！