README.md

metadata

library_name: transformers
language:
  - ur
license: apache-2.0
base_model: GogetaBlueMUI/whisper-medium-ur
tags:
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: Whisper Medium Ur - Muhammad Abdullah on Fleurs
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Fleurs Urdu
          type: google/fleurs
          config: ur_pk
          split: test
          args: 'config: ur_pk, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 22.839213829031493

Whisper Medium Ur - Muhammad Abdullah on Fleurs

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

• Loss: 0.3747
• Wer: 22.8392

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 60
• training_steps: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3288	0.7576	100	0.3701	23.7272
0.1527	1.5152	200	0.3769	23.5496
0.0874	2.2727	300	0.3747	22.8392

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.2
• Tokenizers 0.21.0