README.md

metadata

language:
  - ur
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
metrics:
  - wer
model-index:
  - name: Whisper Small Urdu - darth
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 13
          type: mozilla-foundation/common_voice_13_0
          config: ur
          split: test
          args: ur
        metrics:
          - name: Wer
            type: wer
            value: 59.544821179749185

Whisper Small Urdu - darth

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

• Loss: 0.8511
• Wer Ortho: 62.5039
• Wer: 59.5448

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.673	1.08	500	0.8511	62.5039	59.5448

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3