Edit model card

whisper-small-finetuned-300

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

  • Loss: 0.7359
  • Wer Ortho: 64.8649
  • Wer: 64.8649

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 30
  • training_steps: 300

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
0.5121 20.0 60 1.3011 64.8649 64.8649
0.0001 40.0 120 0.7236 64.8649 64.8649
0.0 60.0 180 0.7314 64.8649 64.8649
0.0 80.0 240 0.7340 64.8649 64.8649
0.0 100.0 300 0.7359 64.8649 64.8649

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
2
Safetensors
Model size
242M params
Tensor type
F32
·
Inference API
or
This model can be loaded on Inference API (serverless).

Finetuned from

Evaluation results