Whisper Small Pt

This model is a fine-tuned version of openai/whisper-small on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2568
  • Wer Ortho: 17.5440
  • Wer: 12.1036

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 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
0.2415 0.2756 500 0.2568 17.5440 12.1036

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu121
  • Datasets 3.3.1
  • Tokenizers 0.21.0
Downloads last month
76
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 SamuelM0422/whisper-small-pt

Finetuned
(2396)
this model

Dataset used to train SamuelM0422/whisper-small-pt

Spaces using SamuelM0422/whisper-small-pt 2

Evaluation results