zhangzijie-pro/Speaker-Verification
Dual-model speech AI toolkit for speaker verification and speaker-aware diarization, with streaming inference, meeting analysis, long-audio monitoring, and speaker-bank integration.
Built on dual-model architecture combining **ResoWave** (joint activity/slot/count prediction) and **REAT** frame embeddings with **GlobalSpeakerTracker** for ID stability across chunked streams. Provides PyPI-installable toolkit with YAML-driven finetuning, Hugging Face model hub integration, and three production workflows: low-latency streaming via chunked inference, meeting timeline extraction with structured JSON output, and persistent monitoring with open-set speaker detection and alert thresholds.
Stars
8
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/zhangzijie-pro/Speaker-Verification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with...
k2-fsa/sherpa
Speech-to-text server framework with next-gen Kaldi
Picovoice/cheetah
On-device streaming speech-to-text engine powered by deep learning
Picovoice/leopard
On-device speech-to-text engine powered by deep learning
zaigie/FunSpeech
开箱即用的本地私有化部署语音服务，快速搭建FunASR与CosyVoice2/3后端