README.md

metadata

language:
  - tr
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
metrics:
  - wer
model-index:
  - name: 'Whisper Large V2 Tr '
    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: tr
        metrics:
          - name: Wer
            type: wer
            value: 10.87659484728129

Whisper Large V2 Tr

This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1700
• Wer: 10.8766

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: 5e-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
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1647	1.0	2738	0.2230	15.6726
0.0574	2.0	5476	0.1874	12.6551
0.0107	3.0	8214	0.1700	10.8766

Framework versions

• Transformers 4.38.1
• Pytorch 2.2.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2