README.md

metadata

datasets:
  - mozilla-foundation/common_voice_11_0
language:
  - ur
metrics:
  - wer
library_name: transformers
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Medium Urdu - Hassaan Butt
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: fleurs
          type: mozilla-foundation/common_voice_11_0
          config: ur
          split: test
          args: 'config: ps, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 32

Whisper Medium Urdu - Hassaan Butt

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

• Wer: 32.0

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.283800	2.92	1000	0.466280	51.433879
0.090300	5.85	2000	0.448847	33.646813
0.036666	8.77	3000	0.420809	32.035004

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.11.0+cu113
• Datasets 11.0
• Tokenizers 0.13.2