metadata
license: mit
tags:
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_pl_10epochs
results: []
speecht5_finetuned_voxpopuli_pl_10epochs
This model is a fine-tuned version of microsoft/speecht5_tts on the facebook/voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.4545
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_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6116 | 1.0 | 210 | 0.5300 |
| 0.5393 | 2.0 | 421 | 0.4871 |
| 0.5235 | 3.0 | 632 | 0.4736 |
| 0.5125 | 4.0 | 843 | 0.4653 |
| 0.5067 | 5.0 | 1053 | 0.4632 |
| 0.5049 | 6.0 | 1264 | 0.4607 |
| 0.4993 | 7.0 | 1475 | 0.4579 |
| 0.4996 | 8.0 | 1686 | 0.4562 |
| 0.4957 | 9.0 | 1896 | 0.4546 |
| 0.4971 | 9.96 | 2100 | 0.4547 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.13.1
- Tokenizers 0.13.3