Silero VAD: pre-trained enterprise-grade Voice Activity Detector
预训练的企业级语音活动检测器,用于实时音频处理
共 1051 个仓库
备份、整理、重新发现你曾点赞过的每一个 GitHub 仓库。
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
预训练的企业级语音活动检测器,用于实时音频处理
SoulX-FlashHead: A unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video generation.
统一1.3B参数框架,用于高保真、无限长度、实时流式肖像视频生成
GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters
鲁棒的开源语音识别模型,含15亿参数
An Open Source Machine Learning Framework for Everyone
用于构建和部署机器学习模型的开源框架