Aller au contenu
ModelPrésentéExterne
Browse files

Breeze ASR 26 GGML

The smallest-footprint build: peak RSS 1.85 GB (Q40), 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...

TypeOtherModèle de baseMediaTek-Research/Breeze-ASR-26VersionRevision 16b8f9aCClasse

Source du modèle

Type
Other
Taille du fichier
848 MB–1,01 GB
Modèle de base
MediaTek-Research/Breeze-ASR-26
Version
vRevision 16b8f9a
Mis à jour
26 oct. 2026
Téléchargements
0
Source
Hugging Face

Description de la source

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:

RepoRuntimeRSSRTF (CPU 4-thread)Best for
Breeze-ASR-26-ct2CTranslate2 / faster-whisper~2.9 GB0.21servers, 8 GB+ hosts, GPU
Breeze-ASR-26-GGMLwhisper.cpp / MacWhisper1.85 GB0.404 GB hosts, desktop apps
Breeze-ASR-26-ONNXsherpa-onnx / onnxruntime—1.3Android / 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.

BuildDiskPeak RSSRTF
Q4_0848 MB1.85 GB0.40
Q5_01.1 GB2.03 GB0.62

Sources

1 source
Hugging FacePrincipalVersion 16b8f9a257a99e0d21baa2667f3ffdc881b8e445
huggingface.co/weemed/Breeze-ASR-26-GGML/tree/16b8f9a257a99e0d21baa2667f3ffdc881b8e445

Vérifié 26 oct.

Download files

Artefacts du modèle

2 artefacts

breeze-q4_0.bin

bin · 848 MB · SHA-256 0e08c5a2d3a5…22ec · Hugging Face

Download file

breeze-q5_0.bin

bin · 1,01 GB · SHA-256 60f25e3a21fe…c449 · Hugging Face

Download file

Extraits de sources

3 extraits

--- 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](https://huggingface.co/weemed/Breeze-ASR-26-ct2) | CTranslate2 / faster-whisper | ~2.9 GB | **0.21** | servers, 8 GB+ hosts, GPU | > | [Breeze-ASR-26-GGML](https://huggingface.co/weemed/Breeze-ASR-26-GGML) | whisper.cpp / MacWhisper | **1.85 GB** | 0.40 | 4 GB hosts, desktop apps | > | [Breeze-ASR-26-ONNX](https://huggingface.co/weemed/Breeze-ASR-26-ONNX) | sherpa-onnx / onnxruntime | — | 1.3 | Android / iOS / WASM | > > All Apache-2.0, derived from [MediaTek-Research/Breeze-ASR-26](https://huggingface.co/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 ```bash # 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 |

Source context: 0 downloads · 1 likes · Pipeline automatic-speech-recognition · Repo weemed/Breeze-ASR-26-GGML

Source context: 0 downloads · 0 likes · Pipeline automatic-speech-recognition · Repo weemed/Breeze-ASR-26-GGML