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
- Merging of dataclasses does not take into acount missing keys could be in nested dictionaries
- Help with replicating the results for wav2vec-u TIMIT
- wav2vec load_model_ensemble_and_task() not working for the example in README
- wav2vec2 feature extraction significantly slower when you run it multiple times
- Encoder attn_mask encounter error in fp16 mode
- AttributeError: 'dict' object has no attribute 'replace' then try to load wav2vec checkpoint
- fix the issue of need_weights is never used in the wav2vec2 model
- Can't get the results on Simultaneous speech-to-text translation as you provide.
- roberta.disambiguate_pronoun : ValueError: max() arg is an empty sequence
- hub_utils: fix logging of src tokens
- Docs
- Python not yet supported