SpeechT5 TTS Hindi JustDial (IISC Female)
This model is a fine-tuned version of microsoft/speecht5_tts on the IISc SYSPINProject Hindi Female Spk001 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4111
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 300
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5369 | 0.9960 | 500 | 0.4684 |
| 0.4995 | 1.9920 | 1000 | 0.4439 |
| 0.479 | 2.9880 | 1500 | 0.4291 |
| 0.4582 | 3.9841 | 2000 | 0.4226 |
| 0.4604 | 4.9801 | 2500 | 0.4176 |
| 0.4583 | 5.9761 | 3000 | 0.4163 |
| 0.455 | 6.9721 | 3500 | 0.4135 |
| 0.4563 | 7.9681 | 4000 | 0.4123 |
| 0.4538 | 8.9641 | 4500 | 0.4131 |
| 0.45 | 9.9602 | 5000 | 0.4111 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 4.8.4
- Tokenizers 0.21.4