README.md

metadata

language:
  - tr
license: apache-2.0
base_model: openai/whisper-large
tags:
  - generated_from_trainer
datasets:
  - custom
metrics:
  - wer
model-index:
  - name: Whisper large tr - baki
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: custom
          type: custom
          args: 'config: tr, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 90.93493367024637

Whisper large tr - baki

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

• Loss: 2.0105
• Wer: 90.9349

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: 40
• training_steps: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.1523	0.9615	100	2.1371	117.2773
1.5102	1.9231	200	1.9995	93.6829
1.1534	2.8846	300	2.0105	90.9349

Framework versions

• Transformers 4.42.3
• Pytorch 2.1.0+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1