README.md

metadata

base_model: openai/whisper-small
datasets:
  - common_voice_13_0
library_name: transformers
license: apache-2.0
metrics:
  - wer
tags:
  - generated_from_trainer
model-index:
  - name: whisper-small-Cantonese-test
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: common_voice_13_0
          type: common_voice_13_0
          config: zh-HK
          split: test
          args: zh-HK
        metrics:
          - type: wer
            value: 71.49724051985046
            name: Wer

whisper-small-Cantonese-test

This model is a fine-tuned version of openai/whisper-small on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3400
• Wer: 71.4972

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: 5e-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: 10
• training_steps: 200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5135	0.1140	100	0.4197	78.8143
0.4537	0.2281	200	0.3400	71.4972

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1