README.md

metadata

license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - common_voice_13_0
metrics:
  - wer
model-index:
  - name: whisper-base-dv
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_13_0
          type: common_voice_13_0
          config: zh-TW
          split: test
          args: zh-TW
        metrics:
          - name: Wer
            type: wer
            value: 61.589139548812135

whisper-base-dv

This model is a fine-tuned version of openai/whisper-base on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3515
• Wer Ortho: 61.0984
• Wer: 61.5891

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.2933	0.17	500	0.3515	61.0984	61.5891

Framework versions

• Transformers 4.37.2
• Pytorch 2.0.1+cu117
• Datasets 2.16.1
• Tokenizers 0.15.1