afaqalinagra/whisper-base-ps

Whisper base Ps Custom 9 Hours dataset- Afaq

This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8107
• Wer: 33.3046
• Cer: 12.9121

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• training_steps: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
No log	2.8341	300	0.6900	42.0667	16.2237
6.3367	5.6635	600	0.6491	35.0054	14.3016
6.3367	8.4929	900	0.7043	34.5533	13.3721
0.4859	11.3223	1200	0.7690	33.2831	12.8686
0.0324	14.1517	1500	0.8107	33.3046	12.9121

Framework versions

• Transformers 5.0.0
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2