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

What are the supported audio languages? #110

Open
andreclaudino opened this issue Dec 8, 2024 · 1 comment
Open

What are the supported audio languages? #110

andreclaudino opened this issue Dec 8, 2024 · 1 comment

Comments

@andreclaudino
Copy link

What are the supported audio languages? I am using the model with ComfyUI, the examples work well with English, but not with Brazilian Portuguese.

Which languages are supported?

@smthemex
Copy link
Owner

smthemex commented Dec 9, 2024

The speech model used whisper tiny, which is a relatively small model and does have good support for English, but I did not test the encoding and decoding performance of other scale models. Because it is troublesome that I cannot confirm whether the results of testing in other languages have achieved the expected effect.
You can try the large speech model in the following link, but you need to modify the code, or you can do the simplest test by changing the name of the large model to whisper-tiny ( in ....comfyui/models/echo_mimic/audio_processor)
download whisper tiny link

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants