Hugging Face's logo

Alperitoo
/
whisper-v3-turbo-common

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Turkish
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
whisper-v3-turbo-common / README.md
Alperitoo's picture
Alperitoo
End of training
3e1bc16 verified
preview code
|
raw
history blame contribute delete
2.3 kB
metadata
library_name: transformers
language:
  - tr
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: 'Whisper Large V3 Turbo FT TR Telephonic - Alperitoo '
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: tr
          split: validation
          args: 'config: turkish, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 15.630747366661094

Whisper Large V3 Turbo FT TR Telephonic - Alperitoo

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1739
  • Wer: 15.6307

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: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1657 0.6154 1000 0.2519 21.1461
0.0993 1.2308 2000 0.2193 19.6685
0.0838 1.8462 3000 0.2031 18.6612
0.0574 2.4615 4000 0.1923 16.5399
0.0247 3.0769 5000 0.1739 15.6307

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.4.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.21.0