README.md

metadata

language:
  - multilingual
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_12_0
metrics:
  - wer
model-index:
  - name: whisper-tiny-zh-TW_Lauren
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_12_0
          config: zh-TW
          split: None
          args: 'config: zh-TW, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 66.11952861952862

whisper-tiny-zh-TW_Lauren

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4621
• Wer: 66.1195

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: 8
• 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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4972	1.4025	1000	0.4668	68.2660
0.2862	2.8050	2000	0.4528	66.2037
0.17	4.2076	3000	0.4583	65.9301
0.1137	5.6101	4000	0.4621	66.1195

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1