Text-to-Speech on VCTK 10H budget v0.92 (train)
9.9WERUnfrozen SPARCLE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Unfrozen SPARCLEInput representation=SPARCLE, Timbre embeddings=with (+T), TTS Backend=ParrotTTS, Adaptation=Fully unfrozen2026.05 | 9.9 | 0.83 | |
| K=3 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=3, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 10.6 | 1.38 | |
| K=7 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=7, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 11 | 0.76 | |
| Unfrozen SPARCLEInput representation=SPARCLE, Timbre embeddings=without (-T), TTS Backend=ParrotTTS, Adaptation=Fully unfrozen2026.05 | 11.3 | 0.94 | |
| K=3 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=3, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 11.4 | 0.98 | |
| K=7 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=7, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 11.4 | 1.17 | |
| K=1 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=1, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 11.6 | 1.02 | |
| K=1 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=1, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 12 | 0.97 | |
| Frozen SPARCLEInput representation=SPARCLE, Timbre embeddings=without (-T), TTS Backend=ParrotTTS, Adaptation=Frozen2026.05 | 13.7 | 1.56 | |
| Char EmbeddingsInput representation=Character, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 14.4 | 1.17 | |
| Frozen SPARCLEInput representation=SPARCLE, Timbre embeddings=with (+T), TTS Backend=ParrotTTS, Adaptation=Frozen2026.05 | 14.8 | 1 | |
| Phone EmbeddingsInput representation=Phoneme, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 25.1 | 1.33 |