home ● blog ● projekte ● termine ● internal ● impressum ● datenschutz

Trace:

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Last revisionBoth sides next revision
projects:verbal_morality_statute [2023/12/27 16:38] – deepnemoprojects:verbal_morality_statute [2024/01/05 21:20] – [Development] kratenko
Line 19: Line 19:
 ===== Development ===== ===== Development =====
  
-The VMSE 2000 is one of the most important projects by Deep Cyber, if not one of the most important efforts of our lifetime. While the physical parameters and technical details have been finalised in an early state of the development back in 2017, the component required for a reliable detection of violations proved do be much more complicated. The depth of Cyber necessary to overcome each and every obstacle on the way of fulfilling our goal, required a prolonged era of research. We are, however, confident, that a significant breakthrough has hence been achieved, and that the project's completion is now imminent.+The VMSE 2000 is one of the most important projects by Deep Cyber, if not one of the most important efforts of our lifetime. While the physical parameters and technical details have been finalised in an early state of the development back in 2017, the component required for a reliable detection of violations proved do be much more complicated. The depth of Cyber necessary to overcome each and every obstacle on the way of fulfilling our goal, required a prolonged era of research. After six years of development we were finally able to present our fully functioning prototype to the public at the very end of 2023 on the perfect event for such a presentation: The Chaos Communication Congress, the 37C3. 
 + 
 +====== Hardware ====== 
 + 
 +- Raspberry Pi 5 (4 also successfully tested) 
 +- Thermal Printer (compatible with `python-escpos`) 
 +- USB Audio Adapter 
 +- PlayStation Eye USB camera for (taped-over CCD) 
 + 
 +====== Software used ====== 
 + 
 +- OpenAI whisper model (base) prompted for your language of choice! 
 +- [[https://github.com/aarnphm/whispercpp|whispercpp python bindings]] 
 +- [https://github.com/openvinotoolkit/openvino|OpenVINO]] for speeding up encoding 
 + 
 +====== Source Code ====== 
 + 
 +You can find the firmware / device glue at [[https://github.com/deepestcyber/vmse2000-firmware/]]. 
 +The voice detection part can be found at [[https://github.com/deepestcyber/vmse2000-detector/]]. 
 + 
 +===== Previous Iterations ===== 
 + 
 +There were a lot of iterations to get to this result (and a lot of non-development as well - this project started in 2017 after all). 
 +We tested DeepSpeech, DeepSpeech V2, RNN on DeepSpeech 2 feature extractors and binary classification RNNs trained from scratch. In the end the simplest and most robust model was OpenAI whisper. Our suspicion is that the amount of data, it's variance and the resulting robustness to noise (microphone as well as background) is what makes the difference. 
 + 
  
 ===== Material needed ===== ===== Material needed =====
Last modified: 2024/01/05 21:34