nassimmasi01/whisper-tiny-en_v6

Whisper tiny En v5 Naji

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5513
• Wer Ortho: 32.2521
• Wer: 23.6211

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: 3e-06
• train_batch_size: 16
• eval_batch_size: 16
• 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: constant_with_warmup
• lr_scheduler_warmup_steps: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.6674	0.1647	100	0.7977	33.5795	25.3814
0.2899	0.3295	200	0.6072	31.9722	23.1000
0.2958	0.4942	300	0.5819	31.3302	23.0437
0.275	0.6590	400	0.5689	30.7414	22.0110
0.2743	0.8237	500	0.5578	31.4075	22.5884
0.2593	0.9885	600	0.5472	31.1854	22.5884
0.211	1.1532	700	0.5539	31.2868	22.7574
0.2128	1.3180	800	0.5513	32.2521	23.6211

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.1+cu126
• Datasets 2.14.6
• Tokenizers 0.21.1