Wav2Seq (from HuBERT-large)

Reported on 1 benchmark across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing1 result

Named Entity Recognition (NER)onSLUE
F1 (%)· 2022-05-02
65.4
best: 69.6 (W2V2-L-LL60K (pipeline approach, uses LM))
Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages arXiv:2205.01086