cgerdes/parakeet-gguf-mirror

Byte-for-byte mirror of the model artifacts the Friend app downloads, kept so a deleted or rewritten upstream cannot break installs (issue #1155).

Generated by scripts/mirror-model-artifacts.sh — do not hand-edit.

Upstream: ggml-org/parakeet-GGUF, a GGUF conversion of NVIDIA's nvidia/parakeet-tdt-0.6b-v3.

The model and its weights originate with NVIDIA and are distributed under CC-BY-4.0. This mirror is tagged cc-by-4.0 on purpose: the conversion repo's own mit tag does not describe the weights it converted, so it is not copied here (issue #1155).

Artifacts

file sha256 bytes upstream repo upstream commit
ggml-parakeet-tdt-0.6b-v3-q8_0.bin 4d64e9e96c2792186d072fde0034df0ad670cf680a2f53069052ead827fd600e 668757119 ggml-org/parakeet-GGUF 35156454d1a39de06863303dd209fd2bed6ee079

Licence: cc-by-4.0. Digests above are the values pinned in Tests/FriendTranscriptionTests/Fixtures/model-artifacts.tsv and verified by the app.

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. 🙋 Ask for provider support