Breeze-ASR-26-GGML / README.md
gloomcheng's picture
Add model card
f23552c verified
|
Raw
History Blame Contribute Delete
1.97 kB
metadata
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