moonshine streaming medium: transcribe.cpp GGUF GGUF conversions of UsefulSensors/moonshine streaming medium for use with transcribe.cpp. Ported from upstream commit 57b8436, pinned 2026 05 06. Validated against the HF Transformers v5.7.0 reference at transcribe.cpp commit 0d312ce on 2026 05 06. Offline English speech to text. A 245M parameter encoder decoder ASR model designed for streaming use (ergodic encoder + sliding window attention, 50 Hz time domain frontend). Same family as moonshine streaming tiny and moonshine streaming small; deepest of the three (14 / 14 layers) and widest hidden dims (encoder 768 / decoder 640). Takes a 16 kHz mono WAV and produces a transcript. No translation, no multilingual capability, no timestamps. Downloads Quantization Download Size WER (LibriSpeech test clean) : : F32 moonshine streaming medium F32.gguf 1015 MB 2.16% F16 moonshine streaming medium F16.gguf 509 MB 2.16% Q8 0 moonshine streaming medium Q8 0.gguf 282 MB 2.16% WER measured on the full LibriSpeech test clean split (2620 utterances) with greedy decoding ( num beams=1 , do sample=False ). F32 reference baseline: 2.16%. Quants are numerically indistinguishable from F32 on this manifes…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy