Edit model card

Whisper Small Urdu - Muhammad Ahmad

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: 0.5270
  • Wer Ortho: 56.1224
  • Wer: 52.7675

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 50
  • training_steps: 700
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Ortho Wer
0.2885 1.0753 500 0.5270 56.1224 52.7675

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.5.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
242M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for ahmadmac/whisper-small-urdu

Finetuned
(1946)
this model

Dataset used to train ahmadmac/whisper-small-urdu

Evaluation results