Update manage.py

[Mkkrishnasai]

Issue at _set_model_item() function
While using fairseq model dataset & model variables are not set

[CLAassistant]

All committers have signed the CLA.

[eginhard]

This is already fixed in our fork (available via pip install coqui-tts). This repo is not updated anymore.

[manuel-84]

After trying this fix I get this error with TTS api

ValueError: [!] Model file not found in the output path

Code:

api = TTS("tts_models/lat/fairseq/vits")
api.tts_with_vc_to_file(
    text,
    speaker_wav="sample.wav",
    file_path="output.wav"
)

[eginhard]

@manuel-84 Can you try just running this:

api = TTS("tts_models/lat/fairseq/vits")
api.tts_to_file(
    text,
    file_path="output.wav"
)

[manuel-84]

@manuel-84 Can you try just running this:

api = TTS("tts_models/lat/fairseq/vits")
api.tts_to_file(
    text,
    file_path="output.wav"
)

Same error... I will try with your repo

[eginhard]

@manuel-84 I just checked and I can use this model without errors. If it still doesn't work with the fork, try removing the tts_models--lat--fairseq--vits/ folder, your download might have been incomplete.

[Mkkrishnasai]

@manuel-84

api = TTS("tts_models/lat/fairseq/vits")
api.tts_with_vc_to_file(
    text,
    speaker_wav="sample.wav",
    file_path="output.wav"
)

ValueError: [!] Model file not found in the output path

"api.tts_with_vc_to_file" is correct as your using "tts_models/lat/fairseq/vits" single language model with voice cloning support.

This could also be because of model download issue.

if Darwin "~/Library/Application\ Support" delete the model and try again.
different for Windows or custom path.

[rose07]

https://tts.byylook.com/ai/text-to-speech

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. You might also look our discussion channels.