You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
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?
The text was updated successfully, but these errors were encountered: