APKs for Speaker diarization

This page lists the speaker diarization APKs for sherpa-onnx, one of the deployment frameworks of the Next-gen Kaldi project.
The name of an APK has the following rule:

sherpa-onnx-{version}-{arch}-speaker-diarization-{segmentation_model}-{embedding_model}.apk

where

version: It specifies the current version, e.g., 1.10.27
arch: The architecture targeted by this APK, e.g., arm64-v8a, armeabi-v7a, x86_64, x86
segmentation_model: The framework for the speaker segmentation model
embedding_model: The framework for the speaker embedding extraction model

Note: Please see https://github.com/k2-fsa/sherpa-onnx/releases/tag/speaker-segmentation-models for a list of supported speaker segmentation models.
Note: Please see https://github.com/k2-fsa/sherpa-onnx/releases/tag/speaker-recongition-models for a list of supported speaker embedding extraction models.

Note about the license The code of Next-gen Kaldi is using Apache-2.0 license. However, we support models from different frameworks. Please check the license of your selected model.

Note about the build script You can find the script for building the APKs at https://github.com/k2-fsa/sherpa-onnx/blob/master/scripts/apk/build-apk-speaker-diarization.sh

APK	Speaker segmentation model	Speaker embedding extraction model
sherpa-onnx-x.y.z-arm64-v8a-speaker-diarization-pyannote_audio-3dspeaker.apk	sherpa-onnx-pyannote-segmentation-3-0.tar.bz2 It is converted from https://huggingface.co/pyannote/segmentation-3.0	3dspeaker_speech_eres2net_base_sv_zh-cn_3dspeaker_16k.onnx It is converted from https://github.com/alibaba-damo-academy/3D-Speaker
sherpa-onnx-x.y.z-arm64-v8a-speaker-diarization-revai_v1-3dspeaker.apk	sherpa-onnx-reverb-diarization-v1.tar.bz2 It is converted from https://huggingface.co/Revai/reverb-diarization-v1	3dspeaker_speech_eres2net_base_sv_zh-cn_3dspeaker_16k.onnx It is converted from https://github.com/alibaba-damo-academy/3D-Speaker