metadata
language:
- es
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper small es - m1
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: fleurs
type: google/fleurs
config: es_419
split: None
args: 'config: es_419, split: test, train'
metrics:
- name: Wer
type: wer
value: 7.583182873355687
Whisper small es - m1
This model is a fine-tuned version of openai/whisper-small on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2369
- Wer: 7.5832
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: 500
- training_steps: 2500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6526 | 2.8571 | 500 | 0.1860 | 7.4972 |
| 0.321 | 5.7143 | 1000 | 0.2052 | 7.2866 |
| 0.0887 | 8.5714 | 1500 | 0.2237 | 7.3639 |
| 0.0429 | 11.4286 | 2000 | 0.2327 | 7.5144 |
| 0.0285 | 14.2857 | 2500 | 0.2369 | 7.5832 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1