wav2vec-bert-korean-dialect-recognition_v1 – AI Model by HERIUN | AlphaNeural AI

You can deploy this model and start earning money today!

HERIUN/
wav2vec-bert-korean-dialect-recognition_v1

like

0

audio-classification

generated_from_trainer

facebook/w2v-bert-2.0

endpoints_compatible

Views

No views yet

Do not use this model. use https://huggingface.co/HERIUN/wav2vec-bert-korean-dialect-recognition

It is trained mini dataset. also evaluation.

wav2vec-bert-korean-dialect-recognition

This model is a fine-tuned version of facebook/w2v-bert-2.0 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6935
Accuracy: 0.7453

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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
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_steps: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1772	1.0	32734	0.9692	0.6393
1.1915	2.0	65468	0.8570	0.6765
1.198	3.0	98202	0.7810	0.7097
1.2072	4.0	130936	0.7748	0.7121
1.2897	5.0	163670	0.7394	0.7252
1.206	6.0	196404	0.7457	0.7196
1.0204	7.0	229138	0.7299	0.7273
1.1207	8.0	261872	0.7225	0.7330
1.3417	9.0	294606	0.6936	0.7450
1.1021	10.0	327340	0.7014	0.7415

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0