ai-charlie
Simple Personal web based on Jekyll theme Moonwalk.
My Projects
-
Planet
DOC
markdown docs、use sphinx.
-
Awesome-SER
MD
papers, datasets, algorithm of Speech Emotion Recognition
-
CPP-Templates
CODE
My cpp template. Use makefile to run cpp files in linux/macos.
Details
-
Blog posts
- 2025-01-09» Docs
- 2025-01-01» Llm
- 2024-01-01» Tensorrt
- 2024-01-01» Object Detect
- 2024-01-01» Numpy Floats
- 2024-01-01» Model Deploy
- 2024-01-01» Cpp
- 2024-01-01» Audio Speech Recognition
- 2024-01-01» Audio Speech Emotion Recognition
- 2023-01-01» Loss
- 2023-01-01» Face Recognition
- 2023-01-01» Deep Learning
- 2023-01-01» Data
- 2023-01-01» Accurary
- 2019-01-01» Transfoms
- 2019-01-01» Nlp
- 2017-01-01» Reactnative
- 2015-01-01» Regex
- 2015-01-01» python-venv-docs
- 2015-01-01» Nvidia Smi
- 2015-01-01» Makefile
- 2015-01-01» linux-docs
- 2015-01-01» Learning Route
- 2015-01-01» Latex
- 2015-01-01» git-docs
- 2015-01-01» Frp Host
- 2015-01-01» Dockerfile
- 2015-01-01» Dockercompose
- 2015-01-01» docker-docs
- 2015-01-01» Dev Tools
- 2015-01-01» Databases
- 2015-01-01» Code Format
- 2015-01-01» Cmake
-
Learning
- computer science
- Face Recognition
- Speech and Language Processing
- CPP Learning
Stars Projects
-
papers-we-love
LEARN
Papers We Love (PWL) is a community built around reading, discussing and learning more about academic computer science papers. This repository serves as a directory of some of the best papers the community can find, bringing together documents scattered across the web. You can also visit the Papers We Love site for more info.
-
ChatGLM-6B
SOTA
ChatGLM-6B 是一个开源的、支持中英双语的对话语言模型，基于 General Language Model (GLM) 架构，具有 62 亿参数。结合模型量化技术，用户可以在消费级的显卡上进行本地部署（INT4 量化级别下最低只需 6GB 显存）。 ChatGLM-6B 使用了和 ChatGPT 相似的技术，针对中文问答和对话进行了优化。经过约 1T 标识符的中英双语训练，辅以监督微调、反馈自助、人类反馈强化学习等技术的加持，62 亿参数的 ChatGLM-6B 已经能生成相当符合人类偏好的回答。
-
FunASR
SOTA
FunASR是一个基础语音识别工具包，提供多种功能，包括语音识别（ASR）、语音端点检测（VAD）、标点恢复、语言模型、说话人验证、说话人分离和多人对话语音识别等。FunASR提供了便捷的脚本和教程，支持预训练好的模型的推理与微调。