mms-1b-all-swagen-male-5hrs-62

This model is a fine-tuned version of facebook/mms-1b-all on the SWAGEN - SWA dataset. It achieves the following results on the evaluation set:

• Loss: 0.2615
• Wer: 0.2013

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 4
• seed: 62
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 30.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
7.2981	0.4854	100	0.8285	0.5493
0.3341	0.9709	200	0.2876	0.2034
0.2691	1.4563	300	0.2647	0.2005
0.2515	1.9417	400	0.2615	0.2013
0.2493	2.4272	500	0.2548	0.2007
0.2421	2.9126	600	0.2551	0.2019
0.2393	3.3981	700	0.2560	0.1984
0.2231	3.8835	800	0.2560	0.1993

Framework versions

• Transformers 4.53.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.0