base_sami_22k_ftallpseudo_ftlabelled_sami_parliament

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 200.0936
• Wer: 0.3922
• Cer: 0.1255

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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_ratio: 0.25
• num_epochs: 60.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
891.9917	1.0	446	200.4455	0.3925	0.1252
737.8926	2.0	892	204.0303	0.4077	0.1323
715.8777	3.0	1338	230.4746	0.4083	0.1277
746.2328	4.0	1784	232.1751	0.4138	0.1403
719.8456	5.0	2230	238.9005	0.4358	0.1442
759.7817	6.0	2676	282.9550	0.4800	0.1564

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1
• Datasets 3.2.0
• Tokenizers 0.21.0