wav2vec2-xls-r-300m-S2P-korean

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 137.7054
• Per: 2.2761
• Learning Rate: 0.0

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use 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: 0.2
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Per	Rate
138.8199	0.4292	200	137.7054	2.2721	0.0
135.2457	0.8584	400	137.7049	2.2730	0.0
135.098	1.2876	600	137.7052	2.2758	0.0
136.7798	1.7167	800	137.7055	2.2758	0.0
136.6869	2.1459	1000	137.7053	2.2768	0.0
135.4296	2.5751	1200	137.7052	2.2723	0.0
137.6503	3.0043	1400	137.7054	2.2761	0.0

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3