metadata
library_name: transformers
language:
- bn
license: mit
base_model: microsoft/speecht5_tts
tags:
- Bengali
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
model-index:
- name: SpeechT5-tuned-bn
results: []
SpeechT5-tuned-bn
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: 0.5377
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
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.7797 | 0.3223 | 100 | 0.6389 |
| 5.1742 | 0.6446 | 200 | 0.6102 |
| 5.0778 | 0.9670 | 300 | 0.5809 |
| 4.8692 | 1.2893 | 400 | 0.5689 |
| 4.7836 | 1.6116 | 500 | 0.5564 |
| 4.7205 | 1.9339 | 600 | 0.5468 |
| 4.6693 | 2.2562 | 700 | 0.5439 |
| 4.59 | 2.5786 | 800 | 0.5423 |
| 4.5718 | 2.9009 | 900 | 0.5377 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1