metadata

language:
  - es
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Es - Carlos Gramajo
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: es
          split: None
          args: 'config: es, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 14.574495770982434

Whisper Small Es - Carlos Gramajo

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.2965
Wer: 14.5745

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: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1142	1.0309	1000	0.2672	15.0677
0.045	2.0619	2000	0.2705	14.4157
0.0185	3.0928	3000	0.2895	14.6389
0.0106	4.1237	4000	0.2965	14.5745

Framework versions

Transformers 4.44.0
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.19.1