atakanince's picture
End of training
b3df6d7 verified
metadata
language:
  - tr
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
metrics:
  - wer
model-index:
  - name: Whisper Small Tr V2 - Atakan Ince
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.1
          type: mozilla-foundation/common_voice_16_1
          config: tr
          split: None
          args: 'config: tr, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 20.395363464821635

Whisper Small Tr V2 - Atakan Ince

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2221
  • Wer: 20.3954

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
0.199 0.37 1000 0.2704 24.3238
0.1476 0.73 2000 0.2443 22.2284
0.0768 1.1 3000 0.2280 20.7674
0.0813 1.46 4000 0.2221 20.3954

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2