metadata
base_model: microsoft/speecht5_tts
datasets:
- voxpopuli
license: mit
tags:
- generated_from_trainer
model-index:
- name: speecht5_tts_voxpopuli_it_v2
results: []
speecht5_tts_voxpopuli_it_v2
This model is a fine-tuned version of microsoft/speecht5_tts on the voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.6262
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-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7564 | 0.6116 | 100 | 0.7051 |
| 0.7636 | 1.2232 | 200 | 0.6764 |
| 0.7263 | 1.8349 | 300 | 0.6662 |
| 0.7262 | 2.4465 | 400 | 0.6555 |
| 0.7038 | 3.0581 | 500 | 0.6483 |
| 0.6931 | 3.6697 | 600 | 0.6422 |
| 0.6881 | 4.2813 | 700 | 0.6344 |
| 0.6916 | 4.8930 | 800 | 0.6300 |
| 0.6814 | 5.5046 | 900 | 0.6286 |
| 0.6692 | 6.1162 | 1000 | 0.6262 |
Framework versions
- Transformers 4.43.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1