README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - speech_commands
metrics:
  - wer
model-index:
  - name: whisper-small-Eng-1
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: speech_commands
          type: speech_commands
          config: v0.01
          split: test
          args: v0.01
        metrics:
          - name: Wer
            type: wer
            value: 239.6

whisper-small-Eng-1

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

• Loss: 5.0620
• Wer: 239.6

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5
• training_steps: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
7.156	0.01	5	6.9727	256.4
7.5392	0.02	10	5.0620	239.6

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3