metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_female_globo_add_token
results: []
speecht5_finetuned_female_globo_add_token
This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3416
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4216 | 7.14 | 1000 | 0.3775 |
| 0.4003 | 14.27 | 2000 | 0.3635 |
| 0.3868 | 21.41 | 3000 | 0.3513 |
| 0.3863 | 28.55 | 4000 | 0.3475 |
| 0.3737 | 35.68 | 5000 | 0.3444 |
| 0.3753 | 42.82 | 6000 | 0.3439 |
| 0.3736 | 49.96 | 7000 | 0.3421 |
| 0.3719 | 57.09 | 8000 | 0.3419 |
| 0.3686 | 64.23 | 9000 | 0.3419 |
| 0.3694 | 71.36 | 10000 | 0.3416 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2