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: 38.063369778089054

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: 0.7296
Wer: 38.0634

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
0.7998	0.7199	1000	0.8235	49.0292
0.5335	1.4399	2000	0.7543	42.1397
0.4172	2.1598	3000	0.7355	40.0646
0.3939	2.8798	4000	0.7296	38.0634

Framework versions

Transformers 4.46.3
Pytorch 2.4.0
Datasets 3.1.0
Tokenizers 0.20.0