metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_fr
results: []
pipeline_tag: text-to-speech
speecht5_finetuned_voxpopuli_fr
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: 0.5054
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: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6907 | 2.01 | 50 | 0.6140 |
| 0.6341 | 4.02 | 100 | 0.5730 |
| 0.5993 | 6.04 | 150 | 0.5417 |
| 0.5707 | 9.0 | 200 | 0.5216 |
| 0.5551 | 11.02 | 250 | 0.5130 |
| 0.5589 | 13.03 | 300 | 0.5110 |
| 0.5447 | 15.04 | 350 | 0.5075 |
| 0.5463 | 18.01 | 400 | 0.5073 |
| 0.5381 | 20.02 | 450 | 0.5057 |
| 0.5409 | 22.03 | 500 | 0.5054 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3