README.md

metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - covost2
metrics:
  - wer
model-index:
  - name: whisper-small-transcription
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: covost2
          type: covost2
          config: zh-CN_en
          split: test
          args: zh-CN_en
        metrics:
          - name: Wer
            type: wer
            value: 73.86688444262964

whisper-small-transcription

This model is a fine-tuned version of openai/whisper-small on the covost2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3107
• Wer: 73.8669

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: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1492	1.3407	1000	0.3107	73.8669

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0