whisper-small-ar-Noise2

This model is a fine-tuned version of MohammedNasri/whisper-small-ar-Noise on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2544
• Wer: 20.9167

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0283	0.21	1000	0.3144	23.5388
0.0543	0.42	2000	0.2991	22.7861
0.083	0.62	3000	0.2827	23.0508
0.087	0.83	4000	0.2611	21.3127
0.0223	1.04	5000	0.2544	20.9167

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.0
• Datasets 2.11.0
• Tokenizers 0.13.2