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: 88.8889
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: 16
- eval_batch_size: 8
- seed: 42
- 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 |
|---|---|---|---|---|
| 0.0 | 2.5 | 10 | nan | 88.8889 |
| 0.0 | 5.0 | 20 | nan | 88.8889 |
| 0.0 | 7.5 | 30 | nan | 88.8889 |
| 0.0 | 10.0 | 40 | nan | 88.8889 |
| 0.0 | 12.5 | 50 | nan | 88.8889 |
| 0.0 | 15.0 | 60 | nan | 88.8889 |
| 0.0 | 17.5 | 70 | nan | 88.8889 |
| 0.0 | 20.0 | 80 | nan | 88.8889 |
| 0.0 | 22.5 | 90 | nan | 88.8889 |
| 0.0 | 25.0 | 100 | nan | 88.8889 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1