Gaffar-21/Whisper-Base-Finetuned-ID

Whisper Base - FineTuned - Id -

This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.8705
• Wer: 45.6110

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch 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: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.891	1.5873	100	0.7102	48.5370
0.3582	3.1746	200	0.7179	45.3528
0.1205	4.7619	300	0.7682	46.2134
0.0413	6.3492	400	0.7906	68.7608
0.0179	7.9365	500	0.8193	57.4010
0.0091	9.5238	600	0.8451	45.3528
0.0064	11.1111	700	0.8578	45.7831
0.0048	12.6984	800	0.8647	45.9552
0.0042	14.2857	900	0.8683	45.6110
0.004	15.8730	1000	0.8705	45.6110

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3