wav2vec2-large-xls-r-300m-korean_senior-colab – AI Model by Gummybear05 | AlphaNeural AI

You can deploy this model and start earning money today!

Gummybear05/
wav2vec2-large-xls-r-300m-korean_senior-colab

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-xls-r-300m

endpoints_compatible

Views

No views yet

wav2vec2-large-xls-r-300m-korean_senior-colab

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: 1.3662
Cer: 0.3521

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: 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: 100
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
23.3703	0.13	200	4.6540	1.0
4.5902	0.26	400	4.6068	1.0
4.5584	0.39	600	4.6189	1.0
4.5187	0.52	800	4.5712	1.0
4.4877	0.64	1000	4.6354	1.0
4.4415	0.77	1200	4.4681	1.0
4.2243	0.9	1400	4.0606	0.8462
3.4216	1.03	1600	3.0853	0.7218
2.7586	1.16	1800	2.6957	0.6083
2.355	1.29	2000	2.4372	0.5711
2.1589	1.42	2200	2.2552	0.5251
2.0473	1.55	2400	2.1381	0.5227
1.8895	1.68	2600	1.9748	0.4967
1.7995	1.81	2800	2.0369	0.4985
1.754	1.93	3000	1.8281	0.4578
1.6027	2.06	3200	1.8280	0.4539
1.5043	2.19	3400	1.7238	0.4285
1.4397	2.32	3600	1.6137	0.4171
1.3416	2.45	3800	1.5148	0.3874
1.2632	2.58	4000	1.5120	0.3840
1.204	2.71	4200	1.4443	0.3741
1.1655	2.84	4400	1.3976	0.3617
1.1657	2.97	4600	1.3662	0.3521

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0