Ubuntu
Initial commit
57280ea
metadata
license: apache-2.0
base_model: nikes64/whisper-small-uk
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-small-uk-v2
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        metrics:
          - name: Wer
            type: wer
            value: 11.2911
language:
  - uk

whisper-small-uk-v2

This model is a fine-tuned version of nikes64/whisper-small-uk on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1369
  • Wer: 11.2911

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • 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
0.087 1.4 1000 0.1092 11.8439
0.0429 2.8 2000 0.1035 11.0597
0.0132 4.2 3000 0.1247 11.1431
0.0067 5.6 4000 0.1369 11.2911

Framework versions

  • Transformers 4.38.0.dev0
  • Pytorch 2.2.0+cu121
  • Datasets 2.17.1
  • Tokenizers 0.15.2