README.md

metadata

language:
  - ur
license: apache-2.0
tags:
  - automatic-speech-recognition
  - hf-asr-leaderboard
  - urdu
  - ur
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Medium Urdu
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0
          type: mozilla-foundation/common_voice_11_0
          args: 'config: ur, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 26.980130911344357

Whisper Medium Urdu

This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 ur dataset. It achieves the following results on the evaluation set:

• Loss: 0.4685
• Wer: 26.9801

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: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 40
• training_steps: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3908	0.48	100	0.5148	30.7061
0.3519	0.97	200	0.4685	26.9801
0.2426	1.45	300	0.4636	28.5023

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2