whisper-small-mn-1 / README.md
bayartsogt's picture
Update README.md
873e833
metadata
language:
  - mn
license: apache-2.0
tags:
  - whisper-event
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-small-mn-1-bayartsogt
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: mn
          split: test
          args:
            language: mn
        metrics:
          - name: Wer
            type: wer
            value: 46.68450950404195

whisper-small-mn-1

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 mn dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4537
  • Wer: 46.6845
  • Cer: 16.1695

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: 32
  • eval_batch_size: 16
  • 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: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Cer
0.1121 4.26 1000 0.4537 46.6845 16.1695

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2