language, license, base_model, tags, datasets, metrics, model-index

language	license	base_model	tags	datasets	metrics	model-index
tr	apache-2.0	openai/whisper-large-v3	generated_from_trainer	mozilla-foundation/common_voice_16_1	wer	name results Whisper Large TR - Özgün Tosun task dataset metrics name type Automatic Speech Recognition automatic-speech-recognition name type config split args Common Voice 16.1 mozilla-foundation/common_voice_16_1 tr None config: tr, split: test name type value Wer wer 11.727918051936383

Whisper Large TR - Özgün Tosun

This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1323
• Wer: 11.7279

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1372	0.3652	1000	0.1810	16.0805
0.1103	0.7305	2000	0.1628	14.5458
0.0563	1.0957	3000	0.1513	12.9302
0.0657	1.4609	4000	0.1383	12.4198
0.0444	1.8262	5000	0.1323	11.7279

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1