README.md

metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - joetan/ep15
metrics:
  - wer
model-index:
  - name: whisper-medium-fine-tuned-ep15
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ep15
          type: joetan/ep15
          args: 'config: en, split: train'
        metrics:
          - name: Wer
            type: wer
            value: 90.83969465648855

whisper-medium-fine-tuned-ep15

This model is a fine-tuned version of openai/whisper-medium on the ep15 dataset. It achieves the following results on the evaluation set:

• Loss: 3.3931
• Wer: 90.8397

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0	100.0	100	3.2156	90.8397
0.0	200.0	200	3.3931	90.8397

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1