whisper-small-sv / README.md
explorall's picture
End of training
8740551
metadata
language:
  - hi
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Hi - Swedish
    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: 97.18480277486489

Whisper Small Hi - Swedish

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: 0.3252
  • Wer: 97.1848

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: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • 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: 500
  • training_steps: 4000

Training results

Training Loss Epoch Step Validation Loss Wer
0.1496 1.29 1000 0.2950 81.4552
0.0532 2.59 2000 0.2897 63.8219
0.0216 3.88 3000 0.3060 90.6321
0.0044 5.18 4000 0.3252 97.1848

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.1.1+cu118
  • Datasets 2.14.7
  • Tokenizers 0.11.0