This is a GGUF-quantized version of NVIDIA's Nemotron-3.5 0.6B automatic speech recognition model. It supports streaming transcription in 28 languages using Conformer-Transducer architecture. The model is optimized for local and on-device inference with tools such as transcribe.cpp and is suitable for developers building offline or privacy-focused voice applications.
Nemotron 3.5 Asr Streaming 0.6b sits in PulseGate's Voice, TTS & speech category. It focuses on converting streaming speech audio into accurate text across 28 languages without depending on closed cloud transcription services. Nemotron 3.5 Asr Streaming 0.6b is an open-source project aimed at developers. The project is open source (MIT). Nemotron 3.5 Asr Streaming 0.6b is available on the web, the command line, and API.
handy-computer builds and maintains Nemotron 3.5 Asr Streaming 0.6b, and the product first shipped in 2026. The project is developed in the open on GitHub with 1.6k stars and 410 commits in the last 90 days. PulseGate's similarity index places it among 8 comparable tools. Among its 4 catalogued features are speech-to-Text, Streaming ASR, and Multilingual Support.
Latest indexed changes and source events
handy-computer/nemotron-3.5-asr-streaming-0.6b-gguf verified by the PulseGate indexer
Other apps tracked under the same category.
