higgs-audio-v3-stt-v2

bosonai/higgs-audio-v3-stt-v2

Speech Recognition2.7B parameterstransformersLicense: apache-2.0

Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗

Downloads 30D: 226
Total downloads: 1,502
Gained 7D: —
Gained 30D: —
Likes: 12
Rank · tracked models: #30,797; 629(down 629 places)this week
Parameters: 2.7B
Last source update: Apr 20, 2026

It moved from #1375 to #1374 among tracked Speech Recognition models this week.

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

higgs-audio-v3-stt-v2 is a speech recognition model published by bosonai. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 1h ago.

Published: Apr 20, 2026
Last updated: Apr 20, 2026
Library: transformers
License: apache-2.0
Task: Speech Recognition
Parameters: 2,675,546,112
Spaces: —
Derivative models: —
Velocity 7D/day: —

transformerssafetensorshiggs_audio_3feature-extractionaudioautomatic-speech-recognitionasrhiggs-audioopen-asr-leaderboardcustom_codeenbase_model:bosonai/higgs-audio-v3-stt

Publisher

bosonaiView publisher statistics →

Derived from bosonai/higgs-audio-v3-stt (reported by the source; parent not yet tracked).

Similar models

Models similar to higgs-audio-v3-stt-v2
Model	Task	DL 30D	Likes	Params
higgs-audio-v3-sttbosonai	Speech Recognition	1,159	41	2.7B
stt-2.6b-en-trfskyutai	Speech Recognition	16.7K	10	2.7B
stt-2.6b-enkyutai	Speech Recognition	0	124	2.6B
canary-qwen-2.5bnvidia	Speech Recognition	26.1K	455	2.6B
MOSS-Transcribe-preview-2BOpenMOSS-Team	Speech Recognition	1,295	49	2.4B
granite-speech-3.3-2bibm-granite	Speech Recognition	282.6K	55	3B