wav2vec2-large-xls-r-300m-korean-convsen2

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: 0.0094
• Cer: 0.0012

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
4.8421	1.0	1762	0.2383	0.0591
0.1721	2.0	3524	0.0309	0.0060
0.065	3.0	5286	0.0094	0.0012

Framework versions

• Transformers 4.17.0
• Pytorch 1.10.0+cu113
• Datasets 2.6.1
• Tokenizers 0.13.1