speecht5_finetuned_sai_charan_v4
This model is a fine-tuned version of SaiCharan0017/speecht5_finetuned_sai_charan_v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3763
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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
- lr_scheduler_warmup_steps: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9616 | 5.3191 | 500 | 0.4451 |
| 1.7679 | 10.6383 | 1000 | 0.4031 |
| 1.6707 | 15.9574 | 1500 | 0.3868 |
| 1.6259 | 21.2766 | 2000 | 0.3844 |
| 1.6019 | 26.5957 | 2500 | 0.3767 |
| 1.594 | 31.9149 | 3000 | 0.3763 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 77
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.