metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_nl
results: []
language:
- nl
library_name: transformers
pipeline_tag: text-to-speech
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: 0.4820
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7445 | 0.43 | 100 | 0.6548 |
| 0.669 | 0.86 | 200 | 0.5961 |
| 0.6065 | 1.29 | 300 | 0.5348 |
| 0.5685 | 1.72 | 400 | 0.5127 |
| 0.5548 | 2.15 | 500 | 0.5006 |
| 0.5443 | 2.58 | 600 | 0.4941 |
| 0.541 | 3.01 | 700 | 0.4885 |
| 0.5297 | 3.44 | 800 | 0.4859 |
| 0.5322 | 3.87 | 900 | 0.4847 |
| 0.5297 | 4.3 | 1000 | 0.4820 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.15.2