120min_mms-1b_Full_FT

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

• Loss: 0.7529
• Wer: 0.5736
• Cer: 0.1789

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.9519	3.0534	100	0.8134	0.6888	0.2178
0.6973	6.1069	200	0.7844	0.6103	0.1918
0.5024	9.1603	300	0.7529	0.5736	0.1789

Framework versions

• Transformers 4.41.1
• Pytorch 2.9.0+cu126
• Datasets 2.21.0
• Tokenizers 0.19.1