README.md

metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - wwwtwwwt/fineaudio-ArtCreativity
metrics:
  - wer
model-index:
  - name: Whisper Tiny En - ArtCreativity - Photography Tips
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: fineaudio-ArtCreativity-Photography Tips
          type: wwwtwwwt/fineaudio-ArtCreativity
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 34.15042216256177

Whisper Tiny En - ArtCreativity - Photography Tips

This model is a fine-tuned version of openai/whisper-tiny on the fineaudio-ArtCreativity-Photography Tips dataset. It achieves the following results on the evaluation set:

• Loss: 0.7095
• Wer: 34.1504

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
0.7104	0.7199	1000	0.7320	36.1841
0.4721	1.4399	2000	0.7127	35.3579
0.3614	2.1598	3000	0.7118	34.7159
0.3472	2.8798	4000	0.7095	34.1504

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.0
• Datasets 3.1.0
• Tokenizers 0.20.0