README.md

metadata

language:
  - nan-tw
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper large-v2 nan-tw only char
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0 nan-tw
          type: mozilla-foundation/common_voice_11_0
          config: nan-tw
          split: test
          args: nan-tw
        metrics:
          - name: Wer
            type: wer
            value: 48.06106870229008

vscode

This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 nan-tw dataset. It achieves the following results on the evaluation set:

• Loss: 0.9147
• Wer: 48.0611
• Cer: 48.1739

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.9198	1.38	1000	0.9147	48.0611	48.1739

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.8.0
• Tokenizers 0.13.2