whisper-tiny-urdu / README.md
darthPanda's picture
update model card README.md
28f4437
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