Repository: localaiLicense: cc-by-4.0
Fluid Speech Mini, a compact English dictation model by FluidVoice built on NVIDIA Parakeet TDT 0.6B v3 and Moondream Parakeet Ultra. Matches Parakeet Ultra accuracy (4.53% WER on Open ASR Leaderboard's 8 public English sets) at about a quarter of the download size (347 MB). Trained to keep transcribing the right speaker when another voice is in the room. Q2_K/Q4_K mixed-precision GGUF for the parakeet-cpp backend; loads in the stock parakeet.cpp runtime on CPU and CUDA.
Links
Tags