-
Notifications
You must be signed in to change notification settings - Fork 278
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
Added Whisper to Benchmark #1762
Conversation
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.
Made a first pass since CI doesnt pass quite yet
FWIW we recently changed policies and we're fine if you simply want to pip install whisper
without having to copy all the model code here, hopefully should make the code easier to review
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.
Can we download assets/
folder as part of CI, basically wget in the install.py script. I'm not sure it's a good idea to merge binary data
@@ -0,0 +1,3 @@ | |||
from .transcribe import cli | |||
|
|||
cli() |
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.
what is the goal of this file?
return model.to(device) | ||
|
||
if __name__ == "__main__": | ||
subprocess.check_call([sys.executable, '-m', 'pip', 'install', '-q', '-r', 'requirements.txt']) |
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.
CI is failing because tiktoken
is not installed, might need to double check working directories
Closing since HF version was merged |
Open to comments and edits - first contribution!