CheeLi03/whisper-base-ar-puct-5k

Whisper Base Arabic Punctuation 5k - Chee Li

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

• Loss: 0.8131
• Wer: 41.0442

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
0.1477	6.6667	1000	0.5514	41.2441
0.0074	13.3333	2000	0.6832	39.8951
0.0022	20.0	3000	0.7561	41.1441
0.0013	26.6667	4000	0.7972	40.8818
0.001	33.3333	5000	0.8131	41.0442

Framework versions

• Transformers 4.43.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1