metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_female2
results: []
speecht5_female2
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: 0.3345
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: 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 |
|---|---|---|---|
| 0.3771 | 7.14 | 1000 | 0.3468 |
| 0.3619 | 14.27 | 2000 | 0.3372 |
| 0.3509 | 21.41 | 3000 | 0.3369 |
| 0.3486 | 28.55 | 4000 | 0.3322 |
| 0.335 | 35.68 | 5000 | 0.3320 |
| 0.3345 | 42.82 | 6000 | 0.3311 |
| 0.3305 | 49.96 | 7000 | 0.3328 |
| 0.328 | 57.09 | 8000 | 0.3332 |
| 0.3242 | 64.23 | 9000 | 0.3339 |
| 0.3234 | 71.36 | 10000 | 0.3345 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2