MediaTek-Research/Breeze-ASR-25 download history

MediaTek-Research/Breeze-ASR-25 is a 1.5B-parameter automatic speech recognition model by MediaTek-Research. In the last 30 days it was downloaded 20,453 times (5,710 in the last 7 days), and 461,572 times in total.

It ranks #5,921 on the Hub by monthly downloads and #282 among automatic speech recognition models.

It has 157 likes.

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

48 models build on Breeze-ASR-25: 24 quantized, 24 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 61,951 times in the last 30 days. See the Breeze-ASR-25 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 2026-11-1820,453+4%
October 202619,648-44%
September 202634,840+37%
August 202625,363-81%
July 2026134,455+877%
June 202613,761+48%
May 20269,328-9%
April 202610,204+48%
March 20266,899+65%
February 20264,179-22%
January 20265,364-22%
December 20256,837-57%

Its busiest 30 days so far ended on 2026-07-24, with 137,195 downloads.

Open MediaTek-Research/Breeze-ASR-25 on Hugging Face

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