wav2vec2-xls-r-300m-kab-5m

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: 3.5241
• Wer: 0.9903
• Cer: 0.7877

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: 7e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
3.3935	50.0	400	3.3441	1.0	1.0
2.7267	100.0	800	3.3977	1.0	1.0
1.734	150.0	1200	3.3134	0.9954	0.9165
1.1978	200.0	1600	3.4363	0.9908	0.8035
0.985	250.0	2000	3.5241	0.9903	0.7877

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1