whisper-small-pashto

This model is a fine-tuned version of ihanif/whisper_small_ps_augmented on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3267
• Wer: 31.5033

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: 5e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 600
• training_steps: 21854
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6737	0.0137	100	0.2825	28.1419
0.5953	0.0275	200	0.2897	28.0859
0.552	0.0412	300	0.2980	29.3557
0.5289	0.0549	400	0.3070	29.9346
0.5475	0.0686	500	0.3189	31.1111
0.4685	0.0824	600	0.3245	32.3436
0.5081	0.0961	700	0.3267	31.5033

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.19.0
• Tokenizers 0.19.1