Fluid Speech Pro

by FluidVoice Labs · Model · Voice & audio

New open model on Hugging Face (automatic-speech-recognition): 0.627B parameters, 2.51 GB of weights, license cc-by-4.0, 5 community quantizations incl. GGUF

AccessOpen weightsNeeds~2.5 GB; smallest build ~0.4 GBDownload2.5 GBSize0.63B parametersLicenseCC BY 4.0