sew
sew copied to clipboard
asappresearch
Hi, Great paper, thank you! I am interested in using the Compact Wave Feature Extractor as specified in your paper (WFE-C-c128-l0), can you point me to the right direction in...
Hi! Thank you for the awesome model! We are very interested in your project and we try to use the sew for Japanese Language. When we train the model, should...
Hello there, I'm trying to train on 8000 Hz sample rate audio dataset. Is it enough to simply add task.sample_rate=8000 to the fairseq command or there are additional config changes...
This PR updates the padding mask calculation to be the same as the one in the reference Wav2Vec2 implementation (same commit as listed in SEW's README): https://github.com/pytorch/fairseq/blob/05255f96410e5b1eaf3bf59b767d5b4b7e2c3a35/fairseq/models/wav2vec/wav2vec2.py#L477 For more details...
