metadata
license: apache-2.0
base_model: nandovallec/whisper-tiny-bg-l
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-order
results: []
whisper-tiny-order
This model is a fine-tuned version of nandovallec/whisper-tiny-bg-l on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0111
- Wer: 0.0
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1524 | 5.0 | 5 | 0.2217 | 11.1111 |
| 0.0766 | 10.0 | 10 | 0.1033 | 8.8889 |
| 0.0347 | 15.0 | 15 | 0.0563 | 11.1111 |
| 0.0166 | 20.0 | 20 | 0.0274 | 2.2222 |
| 0.0084 | 25.0 | 25 | 0.0145 | 0.0 |
| 0.0051 | 30.0 | 30 | 0.0111 | 0.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0