<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
speecht5_finetuned_voxpopuli_es_20k_steps_batch_size_32
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: 0.4376
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 20000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4769 | 21.55 | 5000 | 0.4330 |
| 0.4407 | 43.1 | 10000 | 0.4346 |
| 0.4308 | 64.66 | 15000 | 0.4348 |
| 0.426 | 86.21 | 20000 | 0.4376 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3
