myshell-ai / MeloTTS

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
MIT License
4.87k stars 634 forks source link

fine-tune error koean #182

Open jyjnote opened 3 months ago

jyjnote commented 3 months ago

In my case, I upload the image using Docker.

/app/melo/data# Internal config.json example metadata.list metadata.list.cleaned train.list val.list wavs

The /app/melo/data/wavs folder contains separated learning audio.

There doesn't seem to be anything wrong with converting the contents of train.list and val.list.

The format of my metadata.list is /app/melo/data/wavs/chunk_32.wav||KR|......

but, /app/melo# bash train.sh /app/melo/data/config.json 1 when input shell command

error image

I'm not sure what the problem is