Whisper small - rbcurzon

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

  • Loss: 0.4326
  • Wer Ortho: 18.7768
  • Wer: 17.7896

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 50
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
0.125 2.4631 500 0.4326 18.7768 17.7896

Framework versions

  • Transformers 4.48.3
  • Pytorch 2.5.1+cu124
  • Datasets 3.3.2
  • Tokenizers 0.21.0
Downloads last month
16
Safetensors
Model size
242M params
Tensor type
F32
ยท
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for rbcurzon/whisper-small-fil

Finetuned
(2392)
this model

Dataset used to train rbcurzon/whisper-small-fil

Space using rbcurzon/whisper-small-fil 1

Evaluation results