README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: openai/whisper-medium-en
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: myst-test
          type: asr
          config: en
          split: test
        metrics:
          - type: wer
            value: 8.91
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: cslu_scripted
          type: asr
          config: en
          split: test
        metrics:
          - type: wer
            value: 47.94
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: cslu_spontaneous
          type: asr
          config: en
          split: test
        metrics:
          - type: wer
            value: 25.56
            name: WER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: librispeech
          type: asr
          config: en
          split: testclean
        metrics:
          - type: wer
            value: 3.95
            name: WER

openai/whisper-medium-en

This model is a fine-tuned version of openai/whisper-medium-en on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2578390836715698
• Wer: 8.311953858914759

Training and evaluation data

• Training data: Myst Train (125 hours)
• Evaluation data: Myst Dev (20.9 hours)

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 64
• eval_batch_size: 32
• 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: 10000
• converged_after: 1500