mms_e5_arm_b_uniform

This model is a fine-tuned version of facebook/mms-1b-all on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8653
• Wer: 0.6785
• Cer: 0.4396

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 50
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
9.8314	1.0717	100	2.6154	0.7819	0.5778
5.8763	3.0483	200	2.0488	0.7141	0.4803
5.5840	5.025	300	1.9572	0.6931	0.4526
5.1072	7.0017	400	1.8945	0.6769	0.4449
5.2768	8.0733	500	1.9526	0.6801	0.4430
3.9513	10.05	600	1.8653	0.6785	0.4396

Framework versions

• Transformers 5.0.0
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.22.2