metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- common_voice_16_1
model-index:
- name: speecht5_tts_common_voice_nl
results: []
language:
- nl
pipeline_tag: text-to-speech
speecht5_tts_common_voice_nl
This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3938
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7187 | 1.0 | 441 | 0.4533 |
| 0.4947 | 2.0 | 882 | 0.4243 |
| 0.4648 | 3.0 | 1323 | 0.4131 |
| 0.4468 | 4.0 | 1764 | 0.4062 |
| 0.4384 | 5.0 | 2205 | 0.4016 |
| 0.4362 | 6.0 | 2646 | 0.3982 |
| 0.4309 | 7.0 | 3087 | 0.3964 |
| 0.4317 | 8.0 | 3528 | 0.3959 |
| 0.427 | 9.0 | 3969 | 0.3939 |
| 0.424 | 10.0 | 4410 | 0.3938 |
Framework versions
- Transformers 4.37.2
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.15.2