deepspeech
https://github.com/mozilla/deepspeech
C++
A TensorFlow implementation of Baidu's DeepSpeech architecture
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
C++ not yet supported3 Subscribers
Add a CodeTriage badge to deepspeech
Help out
- Issues
- Change Alphabet::EncodeSingle and Alphabet::DecodeSingle to use an outparam and return an error code instead of calling `abort`
- Install all required macOS dependencies in homebrew cache, don't rely on workers having preinstalled packages
- Add BuildFromBuffer init variant for Java binding
- Add test coverage for "Bytes Are All You Need" mode
- Run LibriSpeech test sets through speaktome-dev and validate accuracy matches local test report
- Leverage libdecoder.a in ds_ctcdecode Python package instead of replicating the build
- Better GitHub issue and pull-request templates
- Add epoch number to all log messages during training
- Training performance drop after augmentation refactoring
- Add progress bars to transcribe.py
- Docs
- C++ not yet supported