fairseq
https://github.com/facebookresearch/fairseq
Python
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
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.
Python not yet supported14 Subscribers
Add a CodeTriage badge to fairseq
Help out
- Issues
- UST - KMeans Clustering & Acoustic Model(s) Missing
- The 'label_smoothed_cross_entropy_with_rdrop.py' file has a bug, preventing validation.
- convert_wav2vec2 to pytorch
- In load_input_to_shared function of fairseq/fairseq/modules /cuda_utils.cu, does it use a negative index risking with undefined behaviour?
- Support videoclip with newer version of dependencies
- Enabling word-level timestamps for all W2L Decoders
- [ASR] Is lexicon-free W2lKenLMDecoder beam search decoding possible with no external language model?
- MMS ASR models without LSAH (language-specific adapters and head) fine-tuning
- Will the NLLB be upgraded on an ongoing basis？
- [Potential Bug] in wav2vec (1.0?): targets always zero, loss computation potentially incorrect?
- Docs
- Python not yet supported