VibeVoice-ASR-4bit is an open-source, quantized version of the VibeVoice-ASR speech-to-text model, optimized for local inference on GPUs with limited memory. It supports multiple languages and is suitable for developers and researchers.
VibeVoice ASR is an Other AI project. It focuses on enabling efficient, local speech-to-text transcription on consumer hardware with limited VRAM. VibeVoice ASR is an open-source project aimed at developers and researchers. VibeVoice ASR is open source under the MIT license. It ships for the command line.
scerz builds and maintains VibeVoice ASR, and it first shipped in 2025. The project is developed in the open on GitHub with 49.4k stars and 49 commits in the last 90 days. Key capabilities include speech recognition, 4-bit quantization, and local inference.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do