README.md

metadata

base_model: openai/whisper-small
datasets:
  - fleurs
language:
  - en
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Small English - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: fleurs
          config: en_us
          split: None
          args: 'config: en split: test'
        metrics:
          - type: wer
            value: 9.362799776910206
            name: Wer

Whisper Small English - 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: 0.3817
• Wer: 9.3628

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
0.0024	5.3191	1000	0.3401	8.9584
0.0004	10.6383	2000	0.3615	9.1327
0.0003	15.9574	3000	0.3759	8.7702
0.0002	21.2766	4000	0.3817	9.3628

Framework versions

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