Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug] Can not run tts with yourtts #4076

Open
alikhabazian opened this issue Dec 14, 2024 · 6 comments
Open

[Bug] Can not run tts with yourtts #4076

alikhabazian opened this issue Dec 14, 2024 · 6 comments
Labels
bug Something isn't working

Comments

@alikhabazian
Copy link

Describe the bug

I tried to run

tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False).to(device)

but after running result to this
[!] Model file not found in the output path

I wanted to run with config of model but could not find that in repo

To Reproduce

import torch
from TTS.api import TTS
device = "cuda" if torch.cuda.is_available() else "cpu"
tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False).to(device)

Expected behavior

No response

Logs

No response

Environment

- last version git documents of coqui-ai/TTS
- ubuntu

Additional context

No response

@alikhabazian alikhabazian added the bug Something isn't working label Dec 14, 2024
@eginhard
Copy link
Contributor

The following code works fine for me:

import torch
from TTS.api import TTS
device = "cuda" if torch.cuda.is_available() else "cpu"
tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts").to(device)
tts.tts_to_file(text="hello", speaker="female-en-5", language="en")

If there is an error about not finding the model file, there might have been an issue with the download. Try deleting the model folder and run that code again. To find that folder:

from trainer.io import get_user_data_dir
print(get_user_data_dir("tts"))

@alikhabazian
Copy link
Author

how did you download the model?

@eginhard
Copy link
Contributor

Running that code downloads the model automatically

@alikhabazian
Copy link
Author

I do not have model folder
I run


tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts").to(device)

but cause to error not find model path

@alikhabazian
Copy link
Author

I don't know how to get model!!

@eginhard
Copy link
Contributor

Please read my previous message:

If there is an error about not finding the model file, there might have been an issue with the download. Try deleting the model folder and run that code again. To find that folder:

from trainer.io import get_user_data_dir
print(get_user_data_dir("tts"))

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants