WMAC

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

• Loss: 0.3746
• Wer: 60.4747

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: 2.5e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 700
• training_steps: 7000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4011	0.4755	1000	0.4190	70.8256
0.2792	0.9510	2000	0.2993	60.8256
0.1901	1.4265	3000	0.2710	61.0217
0.1361	1.9020	4000	0.2524	59.0402
0.0730	2.3776	5000	0.2787	60.8772
0.0592	2.8531	6000	0.2807	60.0826
0.0213	3.3286	7000	0.3746	60.4747

Framework versions

• Transformers 5.2.0
• Pytorch 2.10.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.2