MediaTek-Research/Breeze-ASR-26 download history

MediaTek-Research/Breeze-ASR-26 is a 1.5B-parameter automatic speech recognition model by MediaTek-Research. In the last 30 days it was downloaded 13,466 times (1,881 in the last 7 days), and 105,337 times in total.

It ranks #7,268 on the Hub by monthly downloads and #319 among automatic speech recognition models.

It has 95 likes.

It is a fine-tune of openai/whisper-large-v2.

27 models build on Breeze-ASR-26: 9 quantized, 17 fine-tuned, 1 adapters and 0 merges. Together with the original they were downloaded 15,082 times in the last 30 days. See the Breeze-ASR-26 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 2026-11-1813,466-29%
October 202618,969-52%
September 202639,772+166%
August 202614,972+173%
July 20265,483-10%
June 20266,059+26%
May 20264,795+32%

Its busiest 30 days so far ended on 2026-10-08, with 46,600 downloads.

Open MediaTek-Research/Breeze-ASR-26 on Hugging Face

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