unlearn_speech_commands_wav2vec2-large_random_label_2_42

jialicheng/unlearn_speech_commands_wav2vec2-large_random_label_2_42

unlearn_speech_commands_wav2vec2-large_random_label_2_42 is a audio classification model from jialicheng. Use it for the audio classification task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

11% of all-time downloads

All-time downloads

Public

Parameters

316M

1.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.3 GB · 100%

At a glance

Task: Audio Classification
License: apache-2.0
Model type: wav2vec2
Access: Public
Created: Oct 24, 2025
Updated: Oct 24, 2025
SHA: 0c5b2bc7

Base models

facebook/wav2vec2-large

Datasets

superb

Model card

From the Hugging Face model README

superb_ks_42

This model is a fine-tuned version of facebook/wav2vec2-large on the superb dataset. It achieves the following results on the evaluation set:

Loss: 0.1368
Accuracy: 0.9750
Test Accuracy: 0.9750
Df Accuracy: 0.9569
Unlearn Overall Accuracy: 0.5090
Unlearn Time: 8736.0756

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
0.2332	1.0	1597	0.1091	0.9696	0.5055	0.5055	-1
0.2822	2.0	3194	0.1224	0.9647	0.5062	0.5062	-1
0.3124	3.0	4791	0.1395	0.9687	0.5034	0.5034	-1
0.3215	4.0	6388	0.1368	0.9569	0.5090	0.5090	-1
0.3087	5.0	7985	0.1754	0.9647	0.5034	0.5034	-1
0.2887	6.0	9582	0.1435	0.9647	0.5059	0.5059	-1
0.2808	7.0	11179	0.1272	0.9628	0.5076	0.5076	-1
0.2731	8.0	12776	0.1187	0.9667	0.5065	0.5065	-1
0.2552	9.0	14373	0.1547	0.9647	0.5062	0.5062	-1
0.2556	10.0	15970	0.1349	0.9657	0.5058	0.5058	-1
0.247	11.0	17567	0.1109	0.9667	0.5075	0.5075	-1
0.24	12.0	19164	0.1417	0.9638	0.5080	0.5080	-1
0.2219	13.0	20761	0.1105	0.9696	0.5062	0.5062	-1
0.2156	14.0	22358	0.1172	0.9696	0.5055	0.5055	-1
0.2164	15.0	23955	0.1099	0.9706	0.5054	0.5054	-1
0.2073	16.0	25552	0.1103	0.9706	0.5056	0.5056	-1
0.1968	17.0	27149	0.1011	0.9706	0.5068	0.5068	-1
0.1963	18.0	28746	0.0938	0.9687	0.5082	0.5082	-1
0.1847	19.0	30343	0.0962	0.9706	0.5067	0.5067	-1
0.178	20.0	31940	0.1017	0.9706	0.5064	0.5064	-1

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.18.0
Tokenizers 0.15.2

Task: Audio Classification
Type: wav2vec2
License: apache-2.0
Created: Oct 24, 2025
Updated: Oct 24, 2025