whisper-small-zh / README.md
CheeLi03's picture
Upload tokenizer
6ac0625 verified
metadata
base_model: openai/whisper-small
datasets:
  - fleurs
language:
  - zh
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Small Chinese - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: fleurs
          config: cmn_hans_cn
          split: None
          args: 'config: zh split: test'
        metrics:
          - type: wer
            value: 21.624090369332887
            name: Wer

Whisper Small Chinese - Chee Li

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

  • Loss: 0.2650
  • Wer: 21.6241

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
0.0088 4.3668 1000 0.2373 18.5336
0.0009 8.7336 2000 0.2523 17.6202
0.0005 13.1004 3000 0.2612 21.1278
0.0004 17.4672 4000 0.2650 21.6241

Framework versions

  • Transformers 4.43.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1