zhouwg / kantv

workbench for learing&practising AI tech in real scenario on Android device, powered by GGML(Georgi Gerganov Machine Learning) and NCNN(Tencent NCNN) and FFmpeg

KanTV

KanTV("Kan", aka Chinese PinYin "Kan" or Chinese HanZi "看" or English "watch/listen") , an open source project focus on study and practise state-of-the-art AI technology in real scenario(such as online-TV playback and online-TV transcription(real-time subtitle) and online-TV language translation and online-TV video&audio recording works at the same time) on Android phone/device, derived from original , with much enhancements and new features:

• Watch online TV and local media by my customized , source code of my customized FFmpeg 6.1 could be found in external/ffmpeg according to FFmpeg's license

• Record online TV to automatically generate videos (useful for short video creators to generate short video materials but pls respect IPR of original content creator/provider); record online TV's video / audio content for gather video / audio data which might be required of/useful for AI R&D activity

• AI subtitle(real-time English subtitle for English online-TV(aka OTT TV) by the great & excellent & amazing whisper.cpp ), pls attention Xiaomi 14 or other powerful Android mobile phone is HIGHLY required/recommended for AI subtitle feature otherwise unexpected behavior would happen

• 2D graphic performance

• Set up a customized playlist and then use this software to watch the content of the customized playlist for R&D activity

• UI refactor(closer to real commercial Android application and only English is supported in UI language currently)

• Well-maintained "workbench" for ASR(Automatic Speech Recognition) researchers/developers/programmers who was interested in practise state-of-the-art AI tech(such as whisper.cpp) in real scenario on Android phone/device(PoC: realtime AI subtitle for online-TV(aka OTT TV) on Xiaomi 14 finished from 03/05/2024 to 03/16/2024)

• Well-maintained "workbench" for LLM(Large Language Model) researchers/developers who was interested in practise state-of-the-art AI tech(such as llama.cpp) in real scenario on Android phone/device, or Run/experience LLM model(such as llama-2-7b, baichuan2-7b, qwen1_5-1_8b, gemma-2b) on Android phone/device using the magic llama.cpp

• Well-maintained "workbench" for GGML beginners to study internal mechanism of GGML inference framework on Android phone/device(PoC:Qualcomm QNN backend for ggml finished from 03/29/2024 to 04/26/2024)

• Well-maintained "workbench" for NCNN beginners to study and practise NCNN inference framework on Android phone/device

• Well-maintained turn-key / self-contained project for AI researchers(whom mightbe not familiar with regular Android software development)/developers/beginners focus on edge/device-side AI learning / R&D activity, some AI R&D activities (AI algorithm validation / AI model validation / performance benchmark in ASR, LLM, TTS, NLP, CV......field) could be done by Android Studio IDE + a powerful Android phone very easily

Software architecture of KanTV Android

(depend on #121)

How to build project

Fetch source codes

git clone https://github.com/zhouwg/kantv.git

cd kantv

git checkout master

cd kantv

Setup development environment

Option 1: Setup docker environment

• Build docker image

  docker build build -t kantv --build-arg USER_ID=$(id -u) --build-arg GROUP_ID=$(id -g) --build-arg USER_NAME=$(whoami)

• Run docker container

  # map source code directory into docker container
  docker run -it --name=kantv --volume=`pwd`:/home/`whoami`/kantv kantv
  
  # in docker container
  . build/envsetup.sh
  
  ./build/prebuild-download.sh

Option 2: Setup local environment

• Prerequisites

  Host OS information:
  

  uname -a
  
  Linux 5.8.0-43-generic #49~20.04.1-Ubuntu SMP Fri Feb 5 09:57:56 UTC 2021 x86_64 x86_64 x86_64 GNU/Linux
  
  cat /etc/issue
  
  Ubuntu 20.04.2 LTS \n \l
  
  

  • tools & utilities

  sudo apt-get update
  sudo apt-get install build-essential -y
  sudo apt-get install cmake -y
  sudo apt-get install curl -y
  sudo apt-get install wget -y
  sudo apt-get install python -y
  sudo apt-get install tcl expect -y
  sudo apt-get install nginx -y
  sudo apt-get install git -y
  sudo apt-get install vim -y
  sudo apt-get install spawn-fcgi -y
  sudo apt-get install u-boot-tools -y
  sudo apt-get install ffmpeg -y
  sudo apt-get install openssh-client -y
  sudo apt-get install nasm -y
  sudo apt-get install yasm -y
  sudo apt-get install openjdk-17-jdk -y
  
  sudo dpkg --add-architecture i386
  sudo apt-get install lib32z1 -y
  
  sudo apt-get install -y android-tools-adb android-tools-fastboot autoconf \
          automake bc bison build-essential ccache cscope curl device-tree-compiler \
          expect flex ftp-upload gdisk acpica-tools libattr1-dev libcap-dev \
          libfdt-dev libftdi-dev libglib2.0-dev libhidapi-dev libncurses5-dev \
          libpixman-1-dev libssl-dev libtool make \
          mtools netcat python-crypto python3-crypto python-pyelftools \
          python3-pycryptodome python3-pyelftools python3-serial \
          rsync unzip uuid-dev xdg-utils xterm xz-utils zlib1g-dev
  
  sudo apt-get install python3-pip -y
  sudo apt-get install indent -y
  pip3 install meson ninja
  
  echo "export PATH=/home/`whoami`/.local/bin:\$PATH" >> ~/.bashrc
  
  

  or run below script accordingly after fetch project's source code

  
  ./build/prebuild.sh
  
  
  

  • Android Studio

    download and install Android Studio manually

    Android Studio 4.2.1 or latest Android Studio

  • vim settings

  borrow from http://ffmpeg.org/developer.html#Editor-configuration

  set ai
  set nu
  set expandtab
  set tabstop=4
  set shiftwidth=4
  set softtabstop=4
  set noundofile
  set nobackup
  set fileformat=unix
  set undodir=~/.undodir
  set cindent
  set cinoptions=(0
  " Allow tabs in Makefiles.
  autocmd FileType make,automake set noexpandtab shiftwidth=8 softtabstop=8
  " Trailing whitespace and tabs are forbidden, so highlight them.
  highlight ForbiddenWhitespace ctermbg=red guibg=red
  match ForbiddenWhitespace /\s\+$\|\t/
  " Do not highlight spaces at the end of line while typing on that line.
  autocmd InsertEnter * match ForbiddenWhitespace /\t\|\s\+\%#\@<!$/
  
  

• Download android-ndk-r26c to prebuilts/toolchain, skip this step if android-ndk-r26c is already exist

  . build/envsetup.sh
  
  ./build/prebuild-download.sh
  
  

• Modify ggml/CMakeLists.txt and ncnn/CMakeLists.txt accordingly if target Android device is Xiaomi 14 or Qualcomm Snapdragon 8 Gen 3 SoC based Android phone

• Modify ggml/CMakeLists.txt and ncnn/CMakeLists.txt accordingly if target Android phone is Qualcomm SoC based Android phone and enable QNN backend for inference framework on Qualcomm SoC based Android phone

• Remove the hardcoded debug flag in Android NDK android-ndk issue

  
  # open $ANDROID_NDK/build/cmake/android.toolchain.cmake for ndk < r23
  # or $ANDROID_NDK/build/cmake/android-legacy.toolchain.cmake for ndk >= r23
  # delete "-g" line
  list(APPEND ANDROID_COMPILER_FLAGS
  -g
  -DANDROID
  
  

Build native codes

. build/envsetup.sh

Build Android APK

• Option 1: Build APK from source code by Android Studio IDE

• Option 2: Build APK from source code by command line

    . build/envsetup.sh
    lunch 1
    ./build-all.sh android
  

Run Android APK on Android phone

This project is a learning&research project, so the Android APK will not collect/upload user data in Android device. The Android APK should be works well on any mainstream Android phone(report issue in various Android phone to this project is greatly welcomed) and the following four permissions are required:

• Access to storage is required to generate necessary temporary files
• Access to device information is required to obtain current phone network status information, distinguishing whether the current network is Wi-Fi or mobile when playing online TV
• Access to camera is needed for AI Agent
• Access to mic(audio recorder) is needed for AI Agent

---

here is a short video to demostrate AI subtitle by running the great & excellent & amazing whisper.cpp on a Xiaomi 14 device - fully offline, on-device.

realtime-subtitle-by-whispercpp-demo-on-xiaomi14-finetune-20240324.mp4

---

here is a screenshot to demostrate LLM inference by running the magic llama.cpp on a Xiaomi 14 device - fully offline, on-device.

---

here is a screenshot to demostrate ASR inference by running the excellent whisper.cpp on a Xiaomi 14 device - fully offline, on-device.

---

here are some screenshots to demostrate CV inference by running the excellent ncnn on a Xiaomi 14 device - fully offline, on-device.

some other screenshots

Hot topics

• Android multimodal AI agent(ASR, LLM, TTS, CV, NLP, ..., an open source GPT-4o style multimodal AI agent on Android phone) by GGML + NCNN

• improve the quality of Qualcomm QNN backend for GGML

• bugfix in UI layer(Java)

• bugfix in native layer(C/C++)

Contribution

Be sure to review the opening issues before contribute to project KanTV, We use GitHub issues for tracking requests and bugs, please see how to submit issue in this project .

Report issue in various Android-based phone or even submit PR to this project is greatly welcomed.

Docs

• How to setup customized KanTV server in local dev env
• How to create customized playlist for kantv apk
• How to integrate proprietary/open source codes to project KanTV for personal/proprietary/commercial R&D activity
• How to use whisper.cpp and ffmpeg to add subtitle to video
• How to reduce the size of apk
• How to sign apk
• Acknowledgement
• ChangeLog
• F.A.Q

Special Acknowledgement

AI inference framework
• GGML by Georgi Gerganov
• NCNN by Tencent

AI application engine
• ASR engine whisper.cpp by Georgi Gerganov
• LLM engine llama.cpp by Georgi Gerganov
• ASR engine sherpa-ncnn(an ASR engine using next-generation Kaldi with ncnn) by k2-fsa

This project is suitable for(本项目适合于)

• Students:understand calculus/linear algebra/mathematical statistics and probability theory, have a little / some experiences in C/C++/Java software development, want to learn Android software development(UI, NDK, streamming media, AI application); 学生:了解微积分，线性代数，数理统计与概率论, 且有一定的C/C++/Java开发经验, 希望学习Android开发(UI, NDK, 音视频(FFmpeg), 流媒体(HLS, RTMP, WebRTC), 端侧AI应用);

• Programmers: have good experiences in C/C++ software development, know a little/nothing about real/hardcore AI technology, want to learn AI technology in depth(know how) and validate AI(ASR, TTS, CV, NLP, LLM...) algorithm/model on Android with framework provided in this project easily and quickly(how to validate AI algorithm/model on Android using this project); 程序员:有丰富的C/C++开发经验，几乎不懂真正的AI技术，希望深入学习AI技术(know how)并使用本项目提供的框架在Android设备上快速调试/验证AI特定领域算法/模型(如何使用本项目在Android设备上调试/验证AI特定领域算法/模型);

• Authors/maintainers of AI inference framework: compare the advantages of ggml and ncnn on Android(why focus on ggml & ncnn); AI推理框架的开发人员: 对比两个端侧推理框架ggml与ncnn的优点(为啥只关注ggml与ncnn这两个AI推理框架);

License

Copyright (c) 2021 - 2023 Project KanTV

Copyright (c) 2024 -  Authors of Project KanTV

Licensed under Apachev2.0 or later