metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: Bengali_finetuned_speecht5_tts
results: []
Bengali_finetuned_speecht5_tts
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6113
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- 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
- lr_scheduler_warmup_steps: 100
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.1499 | 1.7419 | 100 | 0.7081 |
| 5.4513 | 3.4902 | 200 | 0.6459 |
| 5.3461 | 5.2386 | 300 | 0.6410 |
| 5.1292 | 6.9805 | 400 | 0.6208 |
| 4.9717 | 8.7289 | 500 | 0.6195 |
| 4.9164 | 10.4772 | 600 | 0.6113 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1