Text-to-Speech on VCTK 1H training budget v0.92
7.5WERK=7 SPARCLE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| K=7 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=7, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 7.5 | 1.13 | |
| Unfrozen SPARCLEInput representation=SPARCLE, Timbre embeddings=with (+T), TTS Backend=ParrotTTS, Adaptation=Fully unfrozen2026.05 | 9.1 | 1.17 | |
| K=3 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=3, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 9.2 | 1.18 | |
| K=7 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=7, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 9.2 | 1.56 | |
| K=3 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=3, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 9.3 | 1.37 | |
| Unfrozen SPARCLEInput representation=SPARCLE, Timbre embeddings=without (-T), TTS Backend=ParrotTTS, Adaptation=Fully unfrozen2026.05 | 11.6 | 1.34 | |
| K=1 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=1, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 12.4 | 1.76 | |
| Frozen SPARCLEInput representation=SPARCLE, Timbre embeddings=without (-T), TTS Backend=ParrotTTS, Adaptation=Frozen2026.05 | 13.7 | 1.02 | |
| K=1 SPARCLEInput representation=SPARCLE, Number of unfrozen layers (K)=1, Timbre embeddings=with (+T), TTS Backend=ParrotTTS2026.05 | 14.3 | 1.37 | |
| Frozen SPARCLEInput representation=SPARCLE, Timbre embeddings=with (+T), TTS Backend=ParrotTTS, Adaptation=Frozen2026.05 | 18 | 1.21 | |
| Char EmbeddingsInput representation=Character, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 24.7 | 1.93 | |
| Phone EmbeddingsInput representation=Phoneme, Timbre embeddings=without (-T), TTS Backend=ParrotTTS2026.05 | 26.8 | 1.59 |