Text-to-Speech on LibriSpeech (other)
4.9CERWhisper + Llama 2 + MMS TTS
Evaluation Results
| Method | Links | |
|---|---|---|
| Whisper + Llama 2 + MMS TTSShots=10, Max context length=2048, Approach=Cascade Topline2024.02 | 4.9 | |
| SPIRIT LM BASE (+ASR+TTS)Shots=10, Max context length=20482024.02 | 7.9 | |
| ASR+TTS onlyShots=10, Max context length=2048, Training=Parallel Data2024.02 | 9.4 | |
| SPIRIT LM BASEShots=10, Max context length=20482024.02 | 43.8 | |
| SPIRIT LM EXPRESSIVEShots=10, Max context length=20482024.02 | 53.6 | |
| Word-level transcriptionShots=10, Max context length=2048, Training=Parallel Data2024.02 | 75.2 |