metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_Mar
results: []
speecht5_finetuned_Mar
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: 0.4845
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- 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: 50
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7023 | 0.7976 | 100 | 0.6419 |
| 0.6105 | 1.5952 | 200 | 0.5699 |
| 0.5895 | 2.3928 | 300 | 0.5631 |
| 0.5796 | 3.1904 | 400 | 0.5530 |
| 0.5818 | 3.9880 | 500 | 0.5388 |
| 0.5448 | 4.7856 | 600 | 0.5399 |
| 0.562 | 5.5833 | 700 | 0.5166 |
| 0.542 | 6.3809 | 800 | 0.5207 |
| 0.5374 | 7.1785 | 900 | 0.5118 |
| 0.5263 | 7.9761 | 1000 | 0.5009 |
| 0.5079 | 8.7737 | 1100 | 0.4965 |
| 0.5108 | 9.5713 | 1200 | 0.4884 |
| 0.497 | 10.3689 | 1300 | 0.4883 |
| 0.4915 | 11.1665 | 1400 | 0.4896 |
| 0.5061 | 11.9641 | 1500 | 0.4845 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3