CngFSt3T_model

This model is a fine-tuned version of openai/whisper-medium on the Marcusxx/CngFSt3T dataset. It achieves the following results on the evaluation set:

• Loss: 0.0744
• Cer: 6.6985

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: 250
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0455	2.2321	1000	0.1281	22.1217
0.0061	4.4643	2000	0.0814	22.4315
0.0008	6.6964	3000	0.0802	5.5849
0.0003	8.9286	4000	0.0747	6.6650
0.0001	11.1607	5000	0.0744	6.6985

Framework versions

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