metadata
license: mit
base_model: Edmon02/speecht5_finetuned_voxpopuli_hy
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
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 common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5088
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: 250
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5974 | 1.2114 | 500 | 0.5489 |
| 0.57 | 2.4228 | 1000 | 0.5261 |
| 0.5684 | 3.6342 | 1500 | 0.5201 |
| 0.5516 | 4.8455 | 2000 | 0.5144 |
| 0.5521 | 6.0569 | 2500 | 0.5134 |
| 0.5436 | 7.2683 | 3000 | 0.5116 |
| 0.5434 | 8.4797 | 3500 | 0.5105 |
| 0.5449 | 9.6911 | 4000 | 0.5088 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1