offiongbassey/efik_xlsr_asr

efik_xlsr

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: 0.2311
• Wer: 0.3078

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: 4
• eval_batch_size: 8
• 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: 500
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.138	0.9488	500	0.6798	0.6791
0.7551	1.8975	1000	0.4455	0.5362
0.594	2.8463	1500	0.3514	0.4507
0.479	3.7951	2000	0.3134	0.3993
0.4288	4.7438	2500	0.2846	0.3670
0.3749	5.6926	3000	0.2523	0.3343
0.3287	6.6414	3500	0.2303	0.3125
0.2732	7.5901	4000	0.2311	0.3078

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.4.2
• Tokenizers 0.22.1