metadata
license: mit
tags:
- generated_from_trainer
datasets:
- voxpopuli
model-index:
- name: speecht5_finetuned_facebook_voxpopuli_spanish
results: []
speecht5_finetuned_facebook_voxpopuli_spanish
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: 0.4434
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5076 | 1.0 | 1074 | 0.4770 |
| 0.4919 | 2.0 | 2148 | 0.4651 |
| 0.4833 | 3.0 | 3222 | 0.4589 |
| 0.4817 | 4.0 | 4296 | 0.4556 |
| 0.4707 | 5.0 | 5370 | 0.4529 |
| 0.4688 | 6.0 | 6444 | 0.4511 |
| 0.4736 | 7.0 | 7518 | 0.4496 |
| 0.4645 | 8.0 | 8592 | 0.4488 |
| 0.4719 | 9.0 | 9666 | 0.4475 |
| 0.4602 | 10.0 | 10740 | 0.4460 |
| 0.4609 | 11.0 | 11814 | 0.4455 |
| 0.4575 | 12.0 | 12888 | 0.4451 |
| 0.458 | 13.0 | 13962 | 0.4440 |
| 0.4601 | 14.0 | 15036 | 0.4438 |
| 0.4647 | 15.0 | 16110 | 0.4441 |
| 0.4591 | 16.0 | 17184 | 0.4436 |
| 0.4535 | 17.0 | 18258 | 0.4428 |
| 0.4615 | 18.0 | 19332 | 0.4430 |
| 0.4549 | 19.0 | 20406 | 0.4426 |
| 0.4569 | 20.0 | 21480 | 0.4434 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3