bosonai/higgs-audio-v3-stt download history

bosonai/higgs-audio-v3-stt is a 2.7B-parameter automatic speech recognition model by bosonai. In the last 30 days it was downloaded 10,807 times (5,344 in the last 7 days), and 24,084 times in total.

It ranks #8,121 on the Hub by monthly downloads and #349 among automatic speech recognition models.

It has 43 likes.

4 models build on higgs-audio-v3-stt: 3 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 12,276 times in the last 30 days. See the higgs-audio-v3-stt galaxy.

Most downloaded derivatives

Downloads by month

Downloads in the 30 days up to the end of each month, and the change from the month before.

MonthDownloadsChange
Up to 2026-11-1810,807+337%
October 20262,473+140%
September 20261,030+2%
August 20261,010-86%
July 20267,105+168%
June 20262,648+2053%
May 2026123-71%
April 2026421+192%

Its busiest 30 days so far ended on 2026-11-18, with 10,807 downloads.

Open bosonai/higgs-audio-v3-stt on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.