Hugging Face's logo

Jasper881108
/
whisper-small-zh

Automatic Speech Recognition
Transformers
PyTorch
whisper
whisper-small
asr
zh-TW
Eval Results
Inference Endpoints
Model card Files Community
1
whisper-small-zh / README.md
Jasper881108's picture
Jasper881108
Create README.md
a878b8c
preview code
|
raw
history blame
1.87 kB
metadata
license: apache-2.0
tags:
  - whisper-small
  - asr
  - zh-TW
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: Whisper Small TW
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0
          type: mozilla-foundation/common_voice_11_0
          config: zh-TW
          split: test
        metrics:
          - type: wer
            value: 9.78
            name: WER

Whisper Medium TW

This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 dataset.

Training and evaluation data

Training:

Evaluation:

Training procedure

  • Datasets were augmented using audiomentations via PitchShift, TimeStretch, Gain, AddGaussianNoise transformations at p=0.3.
  • A space is added between each Chinese character, as demonstrated in the original paper. Effectively, WER == CER in this case.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • gradient_accumulation_steps: 1
  • optimizer: Adam
  • generation_max_length: 225
  • warmup_steps: 500
  • max_steps: 2400
  • fp16: True
  • evaluation_strategy: "steps"

Framework versions

  • Transformers 4.27.1
  • Pytorch 2.0.1+cu120
  • Datasets 2.13.1