KeyError: 'default_vocoder' when run server with voice_conversion_models/multilingual/vctk/freevc24

[nghidinhit]

I met this error when run server with voice_conversion_models/multilingual/vctk/freevc24 model.
Please help.

[nghidinhit]

When I run as the following: docker run --rm -it -p 5002:5002 --entrypoint /bin/bash ghcr.io/coqui-ai/tts-cpu python3 TTS/server/server.py --model_name voice_conversion_models/multilingual/vctk/freevc24 I met the error: Traceback (most recent call last): File "/root/TTS/server/server.py", line 88, in <module> args.vocoder_name = model_item["default_vocoder"] if args.vocoder_name is None else args.vocoder_name KeyError: 'default_vocoder'

…

On Fri, Aug 25, 2023 at 2:22 AM chanveda ***@***.***> wrote: which error ? — Reply to this email directly, view it on GitHub <#2886 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AGKL7KI56CXFQQDNJLC2MULXW6SXNANCNFSM6AAAAAA34SOPSM> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[rohitkrishna094]

How did you fix this?

[krushnapatel-qb]

did you find any solution regarding to this problem???

[eginhard]

I think the server so far only supports (some) TTS models, not VC. PRs welcome in our fork: https://github.com/idiap/coqui-ai-TTS