Q4_0-nemotron-speech-streaming-en-0.6b is an open-source model for real-time English speech recognition. It supports streaming audio input and integrates with the Nemo toolkit, making it suitable for developers building speech-to-text applications.
Q4_0-nemotron-speech-streaming-en-0.6b is a Speech to text project. It focuses on transcribing streaming English audio using an open-source speech recognition model. It is built as an open-source project for AI developers and speech researchers. Q4_0-nemotron-speech-streaming-en-0.6b is open source under the Open Source license. It runs on the command line and API, and it can be self-hosted.
framadhita builds and maintains Q4_0-nemotron-speech-streaming-en-0.6b, and it first shipped in 2026. Among its 4 catalogued features are speech recognition, streaming audio, and english language.
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