README.md

metadata

language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - bika5/pfedrx
metrics:
  - wer
model-index:
  - name: Whisper Small en - bika
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: pfedrx
          type: bika5/pfedrx
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 13.88888888888889

Whisper Small en - bika

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

• Loss: 0.8296
• Wer: 13.8889

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: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0001	1000.0	1000	0.7543	13.8889
0.0	2000.0	2000	0.8129	13.8889
0.0	3000.0	3000	0.8296	13.8889

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1