Speech Recognition On Libricss
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 |
|---|---|---|---|
| GSS + Transducer | 3.30 | GPU-accelerated Guided Source Separation for Meeting Transcription | |
| TS-SEP | 3.27 | TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings |
0 of 2 row(s) selected.