ARK-ASR-3B

Audio8/ARK-ASR-3B

Speech Recognition4.1B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 5, 2026View on Hugging Face ↗
Downloads 30D
16.7K
Total downloads
28.4K
Gained 7D
0
0% vs baseline
Gained 30D
—
Likes
99
+0 in 7D
Rank · tracked models
#6,317
19(up 19 places)this week
Parameters
4.1B
Last source update
Jun 27, 2026
Momentum
4.4

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

ARK-ASR-3B is a speech recognition model published by Audio8. OpenModelStats has tracked the model since Sep 5, 2026, most recently observing it Sep 9, 2026.

Published
Jun 22, 2026
Last updated
Jun 27, 2026
Library
transformers
License
apache-2.0
Task
Speech Recognition
Parameters
4,063,438,848
Spaces
—
Derivative models
1
Velocity 7D/day
0
transformerssafetensorsarkasrtext-generationautomatic-speech-recognitionspeechaudiopytorchvllmark-asrcustom_codezh

Model family

Based on base-model relationships reported by the source's metadata.

Derivative models

Similar models

Models similar to ARK-ASR-3B
ModelDL 30D
ARK-ASR-3BEdge02,639
Audio8-ASR-InfiniteEdge040.1K
Voxtral-Mini-4B-Realtime-2602mistralai1.9M
Voxtral-Mini-4B-Realtime-2602-4bitmlx-community1,290
Voxtral-Mini-4B-Realtime-2602-fp16mlx-community342
Voxtral-Mini-4B-Realtime-6bitmlx-community225
Audio8/ARK-ASR-3B — Downloads, Growth & Stats | OpenModelStats