onemira/nemotron-speech-streaming-en-0.6b-gguf

Byte-identical mirror of NVIDIA's official Q8 GGUF artifact used by OneMira. The model bytes are unmodified. This repository contains the selected GGUF file, not the full upstream training checkpoint. Use the NeMo-Speech.cpp runtime for inference.

Artifact Value
File nemotron-speech-streaming-en-0.6b.q8_0.gguf
Bytes 699872960
SHA-256 d9a01898d2a611c8764e23a1c2f45e70bbd5a425dc4de93692ac951dd603812d
Upstream revision ebe59e5a817142986528bbbee5dba8db7b38ed50

Original modelUpstream model cardLicense copyAttribution

The upstream license and terms apply. Original authorship belongs to NVIDIA; this mirror does not imply NVIDIA endorsement of OneMira.

Downloads last month
65
GGUF
Model size
0.6B params
Architecture
asr
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for onemira/nemotron-speech-streaming-en-0.6b-gguf

Quantized
(26)
this model