Whisper Medium Ur - Jalandhary ASR Fine-Tuned

This model is a fine-tuned version of GogetaBlueMUI/whisper-medium-ur-jalandhary on the Jalandhary ASR dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1395
  • Wer: 18.7094

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: 5e-06
  • train_batch_size: 8
  • 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: 100
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1443 0.4859 500 0.1518 19.8360
0.1315 0.9718 1000 0.1395 18.7094

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.5.1+cu121
  • Datasets 3.3.2
  • Tokenizers 0.21.0
Downloads last month
29
Safetensors
Model size
764M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for GogetaBlueMUI/whisper-medium-ur-jalandhary-v2

Unable to build the model tree, the base model loops to the model itself. Learn more.

Dataset used to train GogetaBlueMUI/whisper-medium-ur-jalandhary-v2

Evaluation results