license: apache-2.0
base_model: MediaTek-Research/Breeze-ASR-26
language:
- zh
- nan
pipeline_tag: automatic-speech-recognition
tags:
- whisper
- whisper.cpp
- ggml
- gguf
- taiwanese-hokkien
- taigi
- macwhisper
- superwhisper
- edge
- quantized
- speech-recognition
Breeze-ASR-26 — GGML (whisper.cpp, Q4_0 / Q5_0)
The smallest-footprint build: peak RSS 1.85 GB (Q4_0), fits a 4 GB host, and loads directly in whisper.cpp desktop apps (MacWhisper Pro, superwhisper) — drag the .bin in, no code. Slower than CT2 (RTF 0.40) but the RAM floor is 1 GB lower.
(Files are whisper.cpp GGML format. whisper.cpp GGUF support is in progress upstream, ggml-org/whisper.cpp#3316; GGUF builds will be added when the toolchain lands.)
Part of the Breeze-ASR-26 edge family — the same MediaTek model in every runtime, pick by your constraint:
Repo Runtime RSS RTF (CPU 4-thread) Best for Breeze-ASR-26-ct2 CTranslate2 / faster-whisper ~2.9 GB 0.21 servers, 8 GB+ hosts, GPU Breeze-ASR-26-GGML whisper.cpp / MacWhisper 1.85 GB 0.40 4 GB hosts, desktop apps Breeze-ASR-26-ONNX sherpa-onnx / onnxruntime — 1.3 Android / iOS / WASM All Apache-2.0, derived from MediaTek-Research/Breeze-ASR-26. Measured on real multi-speaker Mandarin meeting audio. Mandarin does not regress; Taigi is transcribed as Mandarin meaning (not verbatim Taigi characters).
Usage
# whisper.cpp
whisper-cli -m breeze-q5_0.bin -f meeting.wav -l zh -t 4
MacWhisper Pro / superwhisper: download breeze-q5_0.bin, drag it in as a custom model.
| Build | Disk | Peak RSS | RTF |
|---|---|---|---|
| Q4_0 | 848 MB | 1.85 GB | 0.40 |
| Q5_0 | 1.1 GB | 2.03 GB | 0.62 |