|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
--- |
|
|
|
# wav2vec-S-Large-ft-960h |
|
|
|
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-Large-ft-960h was continually pre-trained on the Libri-Light 60kh dataset, and then fine-tuned on the LibriSpeech 960h ASR dataset. |
|
|
|
See our [paper](https://aclanthology.org/2024.findings-acl.681/) for details and check out the [GitHub](https://github.com/biaofuxmu/wav2vec-S/tree/main/wav2vec-S-hf) repository for usage instructions. |
