mdd-arabic-e2-xlsr300m-unannotated-beam

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 13.8083
• Per: 0.8981

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: 24
• eval_batch_size: 24
• seed: 42
• 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
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Per
2.2295	1.0	970	6.8593	0.8932
1.0776	2.0	1940	9.1442	0.8745
0.9818	3.0	2910	10.4151	0.8742
0.7230	4.0	3880	11.1031	0.8738
0.6338	5.0	4850	11.9739	0.8840
0.4782	6.0	5820	12.2693	0.8844
0.4198	7.0	6790	12.8384	0.8755
0.3668	8.0	7760	13.4830	0.8831
0.3602	9.0	8730	13.8083	0.8981

Framework versions

• Transformers 5.14.1
• Pytorch 2.10.0+cu128
• Datasets 5.0.1
• Tokenizers 0.22.2