whisper-tiny-Education-V3

This model is a fine-tuned version of wwwtwwwt/whisper-tiny-no-specific-topic-V3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0906
• Wer: 44.3863

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 500
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7105	0.15	300	1.1709	53.2163
0.7531	1.1075	600	1.0890	52.7614
0.5798	2.065	900	1.0747	48.5443
0.3867	3.0225	1200	1.0781	45.5691
0.2759	3.1725	1500	1.0861	45.8193
0.2285	4.13	1800	1.0906	44.3863

Framework versions

• Transformers 4.50.3
• Pytorch 2.5.1+cu121
• Datasets 3.5.0
• Tokenizers 0.21.0