README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - samromur_children
metrics:
  - wer
model-index:
  - name: whisper_samromur_children
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: samromur_children
          type: samromur_children
          config: samromur_children
          split: validation
          args: samromur_children
        metrics:
          - name: Wer
            type: wer
            value: 122.36095346197501

whisper_samromur_children

This model is a fine-tuned version of openai/whisper-tiny on the samromur_children dataset. It achieves the following results on the evaluation set:

• Loss: 3.4991
• Wer: 122.3610

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: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• training_steps: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.7033	1.0	1	3.4991	122.3610

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1
• Datasets 2.10.0
• Tokenizers 0.13.2