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

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: 0.9497
• Cer: 0.1674

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: 8
• 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0791	3.25	500	0.9497	0.1674
0.0763	6.49	1000	0.9497	0.1674
0.0778	9.74	1500	0.9497	0.1674
0.0782	12.99	2000	0.9497	0.1674
0.0795	16.23	2500	0.9497	0.1674
0.0757	19.48	3000	0.9497	0.1674
0.0782	22.73	3500	0.9497	0.1674
0.0785	25.97	4000	0.9497	0.1674
0.0797	29.22	4500	0.9497	0.1674

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 1.18.3
• Tokenizers 0.13.3