AnalogVector/auglyph-models

Auglyph model artifacts

Public mirror of the model files consumed by Auglyph. Files retain their upstream filenames. This repository combines components under different terms; no single license applies to every file.

Files, sources, and terms

• ggml-large-v3-turbo-q8_0.bin — Whisper Large v3 Turbo Q8_0 artifact. Source: ggerganov/whisper.cpp; the upstream model card identifies the model as MIT-licensed.
• encoder.int8.onnx, decoder.int8.onnx, tokens.txt — Sherpa-ONNX INT8 Canary export based on NVIDIA Canary 1B v2. The conversion is attributed to Sarphix/canary-1b-v2-sherpa-onnx-int8; Canary is CC-BY-4.0.
• timestamps-model.int8.onnx, timestamps-vocab.txt, timestamps-tokenizer.model — CTC timestamp assets attributed to ysdede/nemo-canary-1b-v2-onnx-timestamped, CC-BY-4.0.
• silero_vad.int8.onnx — Silero VAD artifact from the sherpa-onnx ASR model release; see the upstream release for its terms.
• Nemotron-3-Diarization.q8_0.gguf — Q8_0 mirror of NVIDIA Nemotron 3 Diarization, licensed under NVIDIA Open Model License 1.1. The required attribution is in NOTICE, and the agreement is in LICENSES/NVIDIA-Open-Model-License-1.1.pdf.

This is an independent mirror, not an official NVIDIA, OpenAI, or sherpa-onnx repository. Preserve the applicable upstream attributions and licenses when redistributing any file.