metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_voxpopuli_hy
results: []
speecht5_finetuned_voxpopuli_hy
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: 0.6020
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: 62
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3261 | 83.0 | 125 | 0.7073 |
| 0.3063 | 166.67 | 250 | 0.6427 |
| 0.2848 | 250.0 | 375 | 0.6256 |
| 0.2857 | 333.33 | 500 | 0.6221 |
| 0.2838 | 417.0 | 625 | 0.6205 |
| 0.2526 | 500.0 | 750 | 0.6013 |
| 0.2429 | 583.0 | 875 | 0.5997 |
| 0.2666 | 666.67 | 1000 | 0.6097 |
| 0.2531 | 750.0 | 1125 | 0.6119 |
| 0.336 | 833.33 | 1250 | 0.6109 |
| 0.2299 | 917.0 | 1375 | 0.6049 |
| 0.2501 | 1000.0 | 1500 | 0.6020 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0