Breeze-ASR-25

MediaTek-Research/Breeze-ASR-25

Speech Recognition1.5B parametersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
35.3K
Total downloads
428.8K
Gained 7D
+7,675(increase)
1.9%(up) vs baseline
Gained 30D
—
Likes
150
+4 in 7D
Rank · tracked models
#4,491
9(up 9 places)this week
Parameters
1.5B
Last source update
Jul 8, 2025
Momentum
86.2
  • Breeze-ASR-25 gained 7,675 downloads during the last seven tracked days.
  • It moved from #210 to #212 among tracked Speech Recognition models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Breeze-ASR-25 is a speech recognition model published by MediaTek-Research. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 3, 2026.

Published
Jun 6, 2025
Last updated
Jul 8, 2025
Library
—
License
apache-2.0
Task
Speech Recognition
Parameters
1,543,304,960
Spaces
—
Derivative models
5
Velocity 7D/day
1,096
safetensorswhisperautomatic-speech-recognitionzhenarxiv:2506.11130base_model:openai/whisper-large-v2base_model:finetune:openai/whisper-large-v2license:apache-2.0region:us

Publisher

MediaTek-ResearchView publisher statistics →

Derived from openai/whisper-large-v2 (reported by the source; parent not yet tracked).

Model family

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

Similar models

Models similar to Breeze-ASR-25
ModelDL 30D
whisper-large-v2openai79.3K
Breeze-ASR-26MediaTek-Research39.7K
whisper-largeopenai22K
whisper-large-v2-taiwanese-hakka-v1formospeech8,239
asr-whisper-large-v2-saltSunbird2,103
Arabic-Whisper-CodeSwitching-EditionMohamedRashad894
MediaTek-Research/Breeze-ASR-25 — Downloads, Growth & Stats | OpenModelStats