metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
- text-to-speech
datasets:
- facebook/voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_nl
results: []
speecht5_finetuned_voxpopuli_nl
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: 0.4919
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_steps: 500
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7222 | 1.62 | 100 | 0.6410 |
| 0.6791 | 3.25 | 200 | 0.6024 |
| 0.6059 | 4.87 | 300 | 0.5363 |
| 0.564 | 6.49 | 400 | 0.5185 |
| 0.5481 | 8.11 | 500 | 0.5092 |
| 0.5463 | 9.74 | 600 | 0.4998 |
| 0.537 | 11.36 | 700 | 0.4968 |
| 0.5312 | 12.98 | 800 | 0.4913 |
| 0.5275 | 14.6 | 900 | 0.4917 |
| 0.5202 | 16.23 | 1000 | 0.4919 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3