Underdog Bark 3.0 (GGUF)

Unofficial Q8_0 GGUF of ConwayResearch/Underdog-Bark-3.0 at revision 85db2ad18ab41e534a222ee253c29191d77ed919, for transcribe.cpp.

Produced with the files in this repo:

hf download ConwayResearch/Underdog-Bark-3.0 --revision 85db2ad18ab41e534a222ee253c29191d77ed919 --local-dir bark
hf download ConwayResearch/Underdog-Bark-3.0-Pro config.json tokenizer.json --revision 4b5c51e04aa8d16dda9ecdff71bc29f7360149e4 --local-dir meta
python bark_to_hf.py bark meta snapshot   # unpacks model.bark with Conway's bark_loader.py to F32 safetensors
git clone https://github.com/handy-computer/transcribe.cpp && cd transcribe.cpp
git checkout db678a0 && git apply ../convert-parakeet-bark.patch
uv run --project scripts/envs/parakeet scripts/convert-parakeet.py ../snapshot --repo-id underdog-bark-3.0
cmake -B build -DTRANSCRIBE_BUILD_TOOLS=ON && cmake --build build -j
build/bin/transcribe-quantize models/underdog-bark-3.0/underdog-bark-3.0-F32.gguf underdog-bark-3.0-Q8_0.gguf --quant Q8_0

License: CC-BY-4.0, same as the original. See NOTICE.

Downloads last month
11
GGUF
Model size
0.6B params
Architecture
parakeet
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for joshthomasdev/underdog-bark-3.0-gguf

Quantized
(5)
this model