speecht5_tts_ta
This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5678
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3551 | 500.0 | 1000 | 0.4988 |
| 0.3218 | 1000.0 | 2000 | 0.5528 |
| 0.2891 | 1500.0 | 3000 | 0.5593 |
| 0.282 | 2000.0 | 4000 | 0.5678 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for lithish2602/speecht5_tts_ta
Base model
microsoft/speecht5_tts