Text-to-Speech on IndicTTS Database Assamese
3.63MOSGround Truth
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Ground Truth2022.11 | 3.63 | — | — | — | |
| AI4Bharat-TTSAcoustic Model=FastPitch, Vocoder=HiFiGAN2022.11 | 2.39 | 10.93 | 0.38 | — |
| Method | Links | ||||
|---|---|---|---|---|---|
| Ground Truth2022.11 | 3.63 | — | — | — | |
| AI4Bharat-TTSAcoustic Model=FastPitch, Vocoder=HiFiGAN2022.11 | 2.39 | 10.93 | 0.38 | — |