Speech Recognition On Librispeech Train Clean
評価指標
Word Error Rate (WER)
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Word Error Rate (WER) | Paper Title | Repository |
|---|---|---|---|
| wav2vec_wav2letter | 2.8 | Self-training and Pre-training are Complementary for Speech Recognition |
0 of 1 row(s) selected.