A generative speech model for daily dialogue.

PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker/Zotero

Multilingual Voice Understanding Model

Speech To Speech: an effort for an open-sourced and modular GPT4-o

中文情感分析，CNN，BI-LSTM，文本分类

Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.