https://github.com/weixuanz/yack

YACK Automated Comic Kreator
https://github.com/weixuanz/yack

computer-vision speech-to-text

Last synced: 27 days ago
JSON representation

YACK Automated Comic Kreator

• Host: GitHub
• URL: https://github.com/weixuanz/yack
• Owner: WeixuanZ
• License: gpl-3.0
• Created: 2022-01-22T11:02:13.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2022-02-13T16:53:17.000Z (over 4 years ago)
• Last Synced: 2025-02-28T22:12:10.388Z (over 1 year ago)
• Topics: computer-vision, speech-to-text
• Language: Python
• Homepage: https://yack.ml
• Size: 17.9 MB
• Stars: 1
• Watchers: 4
• Forks: 1
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# YACK Automated Comic Kreator

**Hack Cambridge 2022**

Deepgram api is used for speech-to-text, get your key at https://deepgram.com and put it into `./.secrets` as

```env

DEEPGRAM_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

```

dlib Facial Landmark Detector is used, which is available under the Boost Software License

from https://github.com/davisking/dlib. The pretrained weights used are available

from http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2 and should be placed

in `./src/dlib_shape_predictor/`.

To start developing using Docker, simply use

```shell

make run

```

Alternatively, create a virtual environment, and use

```shell

make install

```

## Sample comic

![Thanos webcomic](demo/thanos.png)

"They called me a Mad Man", source: https://youtu.be/fzGBRDpf5GU?t=102