-
Notifications
You must be signed in to change notification settings - Fork 35
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
Tokotron: Tokenized TTS for the SpeechBrain benchmark (single speaker) #37
Tokotron: Tokenized TTS for the SpeechBrain benchmark (single speaker) #37
Conversation
…e fixed for the benchmark
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
since util is only used in TTS.. it would be better to move it to TTS folder
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the wrappers added for all tokenzier are only used in TTS.. so maybe better to cerate the custom_model specific to TTS so it is less confusing.. but the diea is really good . in the next refactoring phase, I will try to apply teh changes across all tokenizers
from huggingface_hub import snapshot_download | ||
|
||
try: | ||
from speechtokenizer import SpeechTokenizer |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
precommit error for unused lib
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
No longer needed given some of the code has been moved out, will update
Thanks @flexthink, everything looks really neat .. I did the review... I have fetched the latest update from the DASB main branch... These are the few comments that I have before merging the PR:
|
Thanks @flexthink for this PR... everything works now..It merged |
No description provided.