README.md

metadata

library_name: transformers
language:
  - ur
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - vfsicoli/common_voice_19_0
metrics:
  - wer
model-index:
  - name: Whisper Medium Ur - Muhammad Abdullah on Common Voice 19
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 19.0
          type: vfsicoli/common_voice_19_0
          config: ur
          split: test
          args: 'config: ur, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 28.99725366735883

Whisper Medium Ur - Muhammad Abdullah on Common Voice 19

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 19.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4106
• Wer: 28.9973

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: 8
• 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: linear
• lr_scheduler_warmup_steps: 60
• training_steps: 600
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3223	0.6682	300	0.4224	27.9903
0.1392	1.3363	600	0.4106	28.9973

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0