Nemotron 3.5 ASR (GGUF)

GGUF conversions of nvidia/nemotron-3.5-asr-streaming-0.6b for use with whisper.cpp.

Available files

  • ggml-nemotron-3.5-asr-streaming-0.6b-f32.bin โ€” Full precision (F32)
  • ggml-nemotron-3.5-asr-streaming-0.6b-f16.bin โ€” Half precision (F16)

Usage

Build parakeet-cli:

git clone -b parakeet-streaming https://github.com/danbev/whisper.cpp.git
cd whisper.cpp
cmake -B build -S .
cmake --build build --target parakeet-cli -j $(nproc)

Download a model (e.g. F16):

hf download danbev/nemotron-asr-streaming-GGUF ggml-nemotron-3.5-asr-streaming-0.6b-f16.bin --local-dir models

Run:

./build/bin/parakeet-cli -m models/ggml-nemotron-3.5-asr-streaming-0.6b-f16.bin -f samples/jfk.wav
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for danbev/nemotron-asr-streaming-GGUF

Finetuned
(27)
this model