# Licenses and Attribution

This repository redistributes model weights created by others. Nothing here is an original
work of the repository owner. Per-file origins and licenses:

## parakeet/ — CC-BY-4.0

`sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8.tar.bz2`

- Original model: [nvidia/parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) by **NVIDIA Corporation**, licensed [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/).
- ONNX int8 export by the [k2-fsa/sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) project (mirrored from its GitHub releases).
- Changes from the original: conversion to ONNX format and int8 quantization (by sherpa-onnx, not by this repository).

## nemotron-en/ — OpenMDW-1.1

`sherpa-onnx-nemotron-speech-streaming-en-0.6b-{80,160,560,1120}ms-int8-2026-04-25.tar.bz2`

- Original model: [nvidia/nemotron-speech-streaming-en-0.6b](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b) by **NVIDIA Corporation**, licensed OpenMDW-1.1 (full text in `OpenMDW-1.1-LICENSE.txt`).
- ONNX int8 exports by the [k2-fsa/sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) project (mirrored from its GitHub releases).

## nemotron35/ — OpenMDW-1.1

`nemotron-3.5-asr-streaming-0.6b-int8.tar.gz`

- Original model: [nvidia/nemotron-3.5-asr-streaming-0.6b](https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b) by **NVIDIA Corporation**, licensed OpenMDW-1.1 (full text in `OpenMDW-1.1-LICENSE.txt`).
- ONNX export via [altunenes/parakeet-rs](https://github.com/altunenes/parakeet-rs) export scripts; int8 quantization mirrored from [smcleod/nemotron-3.5-asr-streaming-0.6b-int8](https://huggingface.co/smcleod/nemotron-3.5-asr-streaming-0.6b-int8).

## llm/ — Apache-2.0

- `Qwen3-4B-Instruct-2507-Q4_K_M.gguf`: original model [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) by **Alibaba Cloud / Qwen team**, [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0). GGUF Q4_K_M quantization by [bartowski](https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF).
- `Qwen2.5-1.5B-Instruct-Q4_K_M.gguf`, `Qwen2.5-0.5B-Instruct-Q4_K_M.gguf`: original models by **Alibaba Cloud / Qwen team**, Apache-2.0. GGUF quantizations by [bartowski](https://huggingface.co/bartowski).

## diarization/

- `sherpa-onnx-pyannote-segmentation-3-0.tar.bz2`: original model [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) by **Hervé Bredin / pyannote**, [MIT](https://opensource.org/license/mit). ONNX export by sherpa-onnx.
- `3dspeaker_speech_eres2net_base_sv_zh-cn_3dspeaker_16k.onnx`: original model from the [3D-Speaker](https://github.com/modelscope/3D-Speaker) project by **Alibaba**, [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0). ONNX export by sherpa-onnx.