metadata
library_name: transformers
language:
- spa
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Tiny Few Audios - vfranchis
results: []
Whisper Tiny Few Audios - vfranchis
This model is a fine-tuned version of openai/whisper-tiny on the Few audios 1.0 dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Wer: 100.0
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.5797 | 3.0769 | 10 | nan | 83.3333 |
| 1.45 | 6.1538 | 20 | nan | 58.3333 |
| 0.5973 | 9.2308 | 30 | nan | 33.3333 |
| 0.234 | 12.3077 | 40 | nan | 33.3333 |
| 0.1089 | 15.3846 | 50 | nan | 25.0 |
| 0.052 | 18.4615 | 60 | nan | 33.3333 |
| 0.0425 | 21.5385 | 70 | nan | 33.3333 |
| 0.2025 | 24.6154 | 80 | nan | 50.0 |
| 1.957 | 27.6923 | 90 | nan | 100.0 |
| 6.8512 | 30.7692 | 100 | nan | 100.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1