whisper-small-hi / README.md
srnsrn120's picture
update model card README.md
755ad7b
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 Hi - srnsrn120
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 40.772877338525355

Whisper Small Hi - srnsrn120

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: 0.3428
  • Wer: 40.7729

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: 400
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2442 0.98 400 0.3428 40.7729

Framework versions

  • Transformers 4.25.0.dev0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.1
  • Tokenizers 0.13.2