Breeze ASR 25: transcribe.cpp GGUF GGUF conversions of MediaTek Research/Breeze ASR 25 for use with transcribe.cpp. Ported from upstream commit cffe7ccb404d025296a00758d0a33468bec3a9d0, pinned 2026 06 29. Validated against the transformers reference at transcribe.cpp commit 3848875 on 2026 06 29. MediaTek Research's Breeze ASR 25 — a fine tune of OpenAI Whisper large v2, converted to GGUF for transcribe.cpp. Optimized for Taiwanese Mandarin (it emits Traditional Chinese ) and English, with explicit support for Mandarin English code switching (intra and inter sentential). Trained on ~11,749 hours: 10,000 h synthetic Mandarin (ODC Synth), 1,738 h English (CommonVoice17) and 11 h real code switch (NTUML2021). Architecturally identical to Whisper large v2 (encoder decoder transformer, 30 second windows with chunked long form decoding); it retains Whisper's 99 language tokenizer, but only Mandarin and English are optimized and validated — other languages remain technically accessible but out of scope. Downloads Quantization Download Size WER (LibriSpeech test clean) CER (FLEURS zh) : : : BF16 Breeze ASR 25 BF16.gguf 3.10 GB 2.29% 8.12% F16 Breeze ASR 25 F16.gguf 3.11 GB 2.29% 8.11% Q8 0…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy