nemotron-speech-streaming-en-0.6b is a compact English automatic speech recognition model developed by NVIDIA using the NeMo framework. It supports streaming inference for real-time transcription and is suitable for integration into applications requiring low-latency speech recognition. The model is publicly available on Hugging Face for local or self-hosted deployment.
In the Speech to text space, Nemotron Speech Streaming En 0.6b takes a focused approach. It focuses on converting English speech to text in real-time streaming scenarios without using proprietary cloud services. It is built as an open-source project for developers. The project is open source (Open Source). Nemotron Speech Streaming En 0.6b is available on the command line and API.
NVIDIA builds and maintains Nemotron Speech Streaming En 0.6b, and it first shipped in 2025. Development happens publicly on GitHub with 42 stars. Among its 3 catalogued features are Speech Recognition, Streaming ASR, and NVIDIA NeMo.
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