pnr-svc/whisper-medium-turkish-speech-v1

Whisper medium tr - Pinar Savci

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

• Loss: 0.1873
• Wer: 15.8254

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: 8
• 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
0.1672	0.2214	1000	0.2599	21.1174
0.1565	0.4429	2000	0.2309	18.6897
0.1534	0.6643	3000	0.2038	17.2712
0.1205	0.8857	4000	0.1873	15.8254

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1