Breeze-ASR-25 is an open-source automatic speech recognition model developed by MediaTek Research, based on the Whisper architecture. It supports both English and Chinese (zh, en) and is available on Hugging Face for integration into applications requiring transcription capabilities. The model has been downloaded over 300k times and is suitable for developers building voice-enabled tools.
Breeze ASR 25 sits in PulseGate's Voice, TTS & speech category. It focuses on converting spoken audio in English and Chinese into accurate text transcripts. It is built as an open-source project for developers. Breeze ASR 25 is open source under the MIT license. The product ships for the web, the command line, and API.
MediaTek Research builds and maintains Breeze ASR 25, and the product first shipped in 2025. Development happens publicly on GitHub with 180 stars. Key capabilities include Speech Recognition, Multilingual Support, and Whisper Architecture.
Latest indexed changes and source events
MediaTek-Research/Breeze-ASR-25 verified by the PulseGate indexer
Other apps tracked under the same category.
