xlsr53-ptbr-mupe-final2

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6446
• Wer: 0.5318
• Cer: 0.2984

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: 2
• eval_batch_size: 2
• 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_steps: 100
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
1.3239	1.0	1500	1.4519	0.5926	0.3194
1.2579	2.0	3000	1.5037	0.5830	0.3204
1.0581	3.0	4500	1.5501	0.5754	0.3114
0.7861	4.0	6000	1.5535	0.5662	0.3092
0.7467	5.0	7500	1.5458	0.5518	0.3066
1.3773	6.0	9000	1.6330	0.5534	0.3023
0.8379	7.0	10500	1.6314	0.5478	0.2960
1.0531	8.0	12000	1.6187	0.5502	0.3027
0.8891	9.0	13500	1.6227	0.5386	0.3004
0.7721	10.0	15000	1.6331	0.5346	0.3001
0.8561	11.0	16500	1.6355	0.5318	0.2988
0.3882	12.0	18000	1.6446	0.5306	0.2982

Framework versions

• Transformers 4.55.0
• Pytorch 2.7.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4