speechbrain 1.0.0

All-in-one speech toolkit in pure Python and Pytorch

Stars: 7802, Watchers: 7802, Forks: 1267, Open Issues: 126

The speechbrain/speechbrain repo was created 3 years ago and the last code push was 34 minutes ago.
The project is extremely popular with a mindblowing 7802 github stars!

How to Install speechbrain

You can install speechbrain using pip

pip install speechbrain

or add it to a project with poetry

poetry add speechbrain

Package Details

Author

Mirco Ravanelli & Others

License

Homepage

https://speechbrain.github.io/

PyPi:

https://pypi.org/project/speechbrain/

GitHub Repo:

https://github.com/speechbrain/speechbrain

Classifiers

Related Packages

Errors

A list of common speechbrain errors.

Code Examples

Here are some speechbrain code examples and snippets.

GitHub Issues

The speechbrain package has 126 open issues on GitHub

• convert "AISHELL-1/ASR/transformer" to onnx or nvidia tensorRT engine
• [Bug]: inference issue when I run ksponSpeech using colab
• [Bug]: RuntimeError: The size of tensor a (140590) must match the size of tensor b (2500) at non-singleton dimension 1
• [Feature Request]: Missing DPTNet recipe?
• Comments on the ESC50 recipes
• K2 interface for speechbrain
• Update DropBox Links
• [Bug]: Python version
• [Bug]: training on VoxCeleb2 cannot reach the 0.8 EER of ECAPA-TDNN on multi-gpu
• Run "on_stage_end" on all processes and save on only a single process
• Training Speaker_ID SpeechBrain
• [Bug]: cannot reach the 0.8 EER of ECAPA-TDNN on multi-gpu
• [Feature Request]: ECAPA-TDNN Model update
• Updating early stopping for more intuitive use
• [Bug]: Huggingface hosted inference API not working for speechbrain/emotion-recognition-wav2vec2-IEMOCAP

See more issues on GitHub