mimba/mms-300-ngiemboon

This model is a fine-tuned version of facebook/mms-300m on the mimba/afrilang dataset. It achieves the following results on the evaluation set:

• Loss: 11.6261
• Wer: 1.0

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
16.6642	1.0	30	12.5842	1.0
16.6642	2.0	60	12.2582	1.0
16.6642	3.0	90	11.6261	1.0

Framework versions

• Transformers 4.57.6
• Pytorch 2.10.0+cu128
• Datasets 2.18.0
• Tokenizers 0.22.2