metadata
language:
- es
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper tiny 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: 18.93646290086837
Whisper tiny es - m1
This model is a fine-tuned version of openai/whisper-tiny on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.4496
- Wer: 18.9365
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: 250
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.2138 | 1.4286 | 250 | 0.4507 | 20.0241 |
| 0.9388 | 2.8571 | 500 | 0.4302 | 18.4378 |
| 0.8286 | 4.2857 | 750 | 0.4378 | 18.7043 |
| 0.7681 | 5.7143 | 1000 | 0.4426 | 18.7645 |
| 0.6715 | 7.1429 | 1250 | 0.4477 | 18.8763 |
| 0.5874 | 8.5714 | 1500 | 0.4496 | 18.9365 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1