metadata

library_name: transformers
language:
  - hi
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 Argentina
    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: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 14.736842105263156

Whisper Small Argentina

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: 0.3638
Wer: 14.7368

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1177	1.4577	1000	0.2907	23.6316
0.0478	2.9155	2000	0.2912	15.5789
0.0075	4.3732	3000	0.3334	20.3158
0.0031	5.8309	4000	0.3531	15.8421
0.0017	7.2886	5000	0.3638	14.7368

Framework versions

Transformers 4.48.0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0