whisper-turbo-tct / README.md
Zakryah's picture
End of training
dbc3905 verified
metadata
library_name: transformers
language:
  - hu
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: TcT Whisper Turbo - Zakryah
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common voice 17.0
          type: mozilla-foundation/common_voice_17_0
          config: hu
          split: test
          args: 'config: hu, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 10.865284788601295

TcT Whisper Turbo - Zakryah

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Common voice 17.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1012
  • Wer: 10.8653

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • 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
0.1832 0.3299 1000 0.1836 18.5993
0.1546 0.6598 2000 0.1450 15.8307
0.1182 0.9898 3000 0.1138 12.4178
0.0435 1.3197 4000 0.1012 10.8653

Framework versions

  • Transformers 4.53.0.dev0
  • Pytorch 2.5.1
  • Datasets 3.3.2
  • Tokenizers 0.21.1