CheeLi03/whisper-ar

Whisper Small - Chee Li

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

• Loss: 0.4791
• Wer: 35.4625

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0147	6.6667	1000	0.3868	34.5125
0.0009	13.3333	2000	0.4417	36.6375
0.0004	20.0	3000	0.4693	35.5625
0.0003	26.6667	4000	0.4791	35.4625

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1