whisper-small-hi / README.md
Wx971025's picture
Update README.md
b36c233
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
    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: 113.49784136121221

whisper-small-hi

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: 4.5728
  • Wer: 113.4978

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 5
  • training_steps: 6
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
3.877 0.01 6 4.5728 19.4978

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.11.0+cu113
  • Datasets 2.7.0
  • Tokenizers 0.13.2