whisper-ckm-9 / README.md
ninninz's picture
End of training
57ec32a verified
|
raw
history blame
2.03 kB
metadata
language:
  - cr
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - generated_from_trainer
datasets:
  - audiofolder
metrics:
  - wer
model-index:
  - name: whisper-large-v3-croarian_overlap_removed_30
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: train
          args: 'config: cr, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 82.7174045615319

whisper-large-v3-croarian_overlap_removed_30

This model is a fine-tuned version of openai/whisper-large-v3 on the audiofolder dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5767
  • Wer: 82.7174

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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0275 22.22 1000 2.2397 76.3508
0.0075 44.44 2000 2.3756 75.8507
0.0024 66.67 3000 2.5384 83.9005
0.0021 88.89 4000 2.5767 82.7174

Framework versions

  • Transformers 4.37.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.1