metadata
license: mit
base_model: Edmon02/speecht5_finetuned_voxpopuli_hy
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_voxpopuli_hy
results: []
speecht5_finetuned_voxpopuli_hy
This model is a fine-tuned version of Edmon02/speecht5_finetuned_voxpopuli_hy on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6183
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: 2e-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: 1000
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6306 | 57.1429 | 500 | 0.6027 |
| 0.6062 | 114.2857 | 1000 | 0.6026 |
| 0.5872 | 171.4286 | 1500 | 0.6059 |
| 0.5767 | 228.5714 | 2000 | 0.6197 |
| 0.5672 | 285.7143 | 2500 | 0.6145 |
| 0.5605 | 342.8571 | 3000 | 0.6194 |
| 0.5569 | 400.0 | 3500 | 0.6195 |
| 0.5552 | 457.1429 | 4000 | 0.6183 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1