mms-zul-finetuned

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

• Loss: 0.1072
• Wer: 0.1908
• Cer: 0.0260

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
1.0437	0.7105	100	0.1440	0.2392	0.0338
0.7657	1.0	141	0.1072	0.1908	0.0260

Framework versions

• Transformers 5.5.4
• Pytorch 2.7.1+cu118
• Datasets 4.8.4
• Tokenizers 0.22.2