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.binโ Full precision (F32)ggml-nemotron-3.5-asr-streaming-0.6b-f16.binโ 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
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for danbev/nemotron-asr-streaming-GGUF
Base model
nvidia/nemotron-3.5-asr-streaming-0.6b