whisper-small / README.md
varunril's picture
Upload 11 files
c1e37fe verified
metadata
language:
  - hi
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Odia - Auro Tripathy with tips from Sanchit language None
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: or
          split: test
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 59.75958786491128

Whisper Small Odia - Auro Tripathy with tips from Sanchit language None

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5753
  • Wer: 59.7596

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0036 20.0 1000 0.3950 60.8472
0.0016 40.0 2000 0.4374 61.1906
0.0001 60.0 3000 0.5229 59.5306
0.0 80.0 4000 0.5753 59.7596

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.1+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2