We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
After i updated the whisperx i am getting this error while transcribing using large-v3. Anyone else facing same?
ValueError: Invalid input features shape: expected an input with shape (1, 128, 3000), but got an input with shape (1, 80, 3000) instead
The text was updated successfully, but these errors were encountered:
Maybe same issue with #582 , please make sure you use the Systran HF model (https://huggingface.co/Systran/faster-whisper-large-v3) and update to the latest version 0.10.0
Sorry, something went wrong.
I get the same error with the OpenAI model, but only if I quantize to int8. When I don't apply quantization it works fine.
No branches or pull requests
After i updated the whisperx i am getting this error while transcribing using large-v3. Anyone else facing same?
ValueError: Invalid input features shape: expected an input with shape (1, 128, 3000), but got an input with shape (1, 80, 3000) instead
The text was updated successfully, but these errors were encountered: