hubert-esc50-finetuned-v2 – AI Model by cj94 | AlphaNeural AI

You can deploy this model and start earning money today!

cj94/
hubert-esc50-finetuned-v2

like

0

audio-classification

generated_from_trainer

facebook/hubert-base-ls960

endpoints_compatible

Views

No views yet

hubert-esc50-finetuned-v2

This model is a fine-tuned version of facebook/hubert-base-ls960 on the ESC-50 dataset. It achieves the following results on the evaluation set:

Loss: 1.8640
Accuracy: 0.5225

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.5023	1.0	200	3.4954	0.1025
3.0745	2.0	400	3.1206	0.14
2.7667	3.0	600	2.8674	0.18
2.5477	4.0	800	2.6013	0.265
2.3458	5.0	1000	2.5071	0.3125
2.3287	6.0	1200	2.2673	0.395
1.9078	7.0	1400	2.1068	0.4425
1.8707	8.0	1600	2.0044	0.4775
1.7355	9.0	1800	1.8945	0.52
1.7396	10.0	2000	1.8640	0.5225

Framework versions

Transformers 4.40.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1