CngFSt10sec_model

This model is a fine-tuned version of openai/whisper-medium on the Marcusxx/CngFSt10sec dataset. It achieves the following results on the evaluation set:

• Loss: 0.0530
• Cer: 20.6694

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0073	8.2645	1000	0.0529	75.3624
0.0007	16.5289	2000	0.0493	21.5972
0.0002	24.7934	3000	0.0510	11.1755
0.0001	33.0579	4000	0.0522	19.4764
0.0001	41.3223	5000	0.0530	20.6694

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.2+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1