unlearn_speech_commands_hubert-base_scrub_8_42 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn_speech_commands_hubert-base_scrub_8_42

like

0

audio-classification

generated_from_trainer

facebook/hubert-base-ls960

Views

No views yet

superb_ks_42

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

Loss: 357.6496
Accuracy: 0.6209
Test Accuracy: 0.6209
Df Accuracy: 0.1400
Unlearn Overall Accuracy: 0.7405
Unlearn Time: 1233.4991

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: 32
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_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
0.0	1.0	1469	357.6496	0.1400	0.7405	0.7405	-1
0.0	2.0	2938	1387.4460	0.1400	0.7405	0.7405	-1
0.0	3.0	4407	2685.7893	0.1400	0.7405	0.7405	-1
0.0	4.0	5876	3744.4666	0.1400	0.7405	0.7405	-1
0.0	5.0	7345	4154.5615	0.1400	0.7405	0.7405	-1

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.18.0
Tokenizers 0.15.2