whisper-tiny-zh / README.md
mg5812's picture
update model card README.md
196f46c
metadata
language:
  - zh
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Tiny Zh - Sanchit Gandhi
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: zh-CN
          split: test
          args: 'config: zh, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 111.34001134001134

Whisper Tiny Zh - Sanchit Gandhi

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: 0.5909
  • Wer: 111.3400

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
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.7098 0.4 1000 0.6905 106.4733
0.7108 0.81 2000 0.6273 106.5394
0.6124 1.21 3000 0.6009 112.0582
0.5633 1.61 4000 0.5909 111.3400

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3