File size: 464 Bytes
3605328 |
1 2 3 4 5 6 7 |
# wav2vec-S-Base
wav2vec-S is a streaming variant of wav2vec 2.0, designed to maintain consistent representations between training and inference for streaming speech processing.
wav2vec-S-Base was continually pre-trained on the LibriSpeech 960h dataset.
See our [paper](https://aclanthology.org/2024.findings-acl.681/) for details and check out the [GitHub](https://github.com/biaofuxmu/wav2vec-S/wav2vec-S-hf/README.md) repository for usage instructions. |