wav2vec2-xls-r-akan-20-hours

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: 0.7073
• Wer: 0.3412
• Cer: 0.1076

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: 32
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• 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_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
7.3146	8.6207	500	0.6110	0.5235	0.1637
0.8982	17.2414	1000	0.4489	0.3460	0.1094
0.4994	25.8621	1500	0.5257	0.3517	0.1119
0.3055	34.4828	2000	0.6314	0.3488	0.1104
0.2151	43.1034	2500	0.7073	0.3412	0.1076

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3