Gaffar-21/Whisper-Tiny-finetuned-id

Whisper Tiny - FineTuned - Id -

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

• Loss: 1.0871
• Wer: 65.5766

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
1.1857	1.5873	100	0.9525	64.8881
0.5773	3.1746	200	0.9205	59.1222
0.2841	4.7619	300	0.9536	59.2943
0.138	6.3492	400	0.9851	54.3890
0.0694	7.9365	500	1.0057	59.6386
0.0339	9.5238	600	1.0530	64.8021
0.0195	11.1111	700	1.0620	61.1876
0.013	12.6984	800	1.0752	57.1429
0.0106	14.2857	900	1.0827	65.4045
0.0097	15.8730	1000	1.0871	65.5766

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Tokenizers 0.20.3