Text-to-Speech on IndicTTS Database Telugu
4.42MOSGround Truth
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Ground Truth2022.11 | 4.42 | — | — | 27.3 | |
| AI4Bharat-TTSAcoustic Model=FastPitch, Vocoder=HiFiGAN2022.11 | 3.66 | 9.91 | 0.36 | 26.6 | |
| Tacotron2+WaveGlowAcoustic Model=Tacotron2, Vocoder=WaveGlow2022.11 | 3.4 | 11.03 | 0.38 | 225.4 | |
| GlowTTS+HiFiGANAcoustic Model=GlowTTS, Vocoder=HiFiGAN2022.11 | 2.61 | 7.16 | 0.37 | 36.4 |