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
- Use omegaconf to load S2T data config YAML
- some confusions about reproducible results
- Add pretrained conformer model for the "Wav2Vec 2.0 Large (LV-60 + CV + SWBD + FSH) 960 hours Librispeech" settings
- How is the LSTM-based Encoder Decoder trained for translation?
- Add scoring WER/BLEU in speech_to_text
- Why the model parameters decreased after using FSDP ?
- ### Unable to perform Evaluation / Inference in wav2vec2.0 model
- NameError: name 'CriterionType' is not defined [wav2vec2 evaluation using stt.py]
- implementation of Mask-Predict: Parallel Decoding of Conditional Masked Language Models (Ghazvininejad et al., 2019)
- nonautoregressive models' scripts are missing
- Docs
- Python not yet supported