Streaming Sortformer Diarizer 4spk v2.1 — GGUF (for transcribe.cpp)
GGUF conversion of NVIDIA's
diar_streaming_sortformer_4spk-v2.1
(checkpoint commit fafaab5) for the
transcribe.cpp engine,
produced with the repo's own scripts/convert-sortformer.py at commit 553f109.
Provenance & caveats
- Independent conversion for integration testing (Isaree on-device scribe), not an official artifact of either upstream project.
- Q8_0 reproduces the F32 reference speaker boundaries exactly on the engine's 2-speaker fixture; formal DER has not been re-measured on this artifact.
- No K-quants by upstream policy: k-tier weight error can deterministically permute speaker labels mid-stream. Use Q8_0 (or F16).
- Standalone diarizer: emits speaker segments only, no transcript. 4-speaker cap, arrival-order labels.
Original model © NVIDIA, under the NVIDIA Open Model License (see link above).
- Downloads last month
- 61
Hardware compatibility
Log In to add your hardware
8-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Adit2K/diar_streaming_sortformer_4spk-v2.1-gguf
Base model
nvidia/diar_streaming_sortformer_4spk-v2.1