juancopi81's picture
Update README.md
ceeaee5
metadata
language:
  - es
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Medium Es - Fleurs + Common Voice
    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: test
          args: es
        metrics:
          - name: Wer
            type: wer
            value: 6.0742684891637655

Whisper Small Es - Sanchit Gandhi

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: 0.1883
  • Wer: 6.0743

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: 32
  • eval_batch_size: 16
  • 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: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0694 0.2 1000 0.2194 6.8194
0.0336 0.4 2000 0.2097 6.7558
0.0221 0.6 3000 0.2068 6.4952
0.0266 0.8 4000 0.1950 6.2841
0.0256 1.0 5000 0.1883 6.0743

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2