Nik Vaessen
Machine Learning Engineer at Vox AI
Amsterdam, North Holland, Netherlands
Summary
🤩
Rockstar🎓
Top SchoolNik Vaessen is a Machine Learning Engineer with a decade of experience building speech-to-text systems and production-ready backend services, currently driving automated drive-thru ASR solutions at Vox AI. He holds a PhD in Machine Learning from Radboud University and has combined academic research in speech representation learning with hands-on engineering across Jitsi, Jigasi and other open-source projects. Nik’s contributions include practical fixes and test coverage improvements to the widely used jiwer WER/CER evaluation library and engineering transcription integrations that work around real-world API limits. He has applied responsible AI research at Amazon AGI and a track record of shipping end-to-end systems spanning high-performance HPC environments, cloud SDKs, and real-time media sessions. Pragmatic and detail-oriented, he often focuses on robustness and edge cases—non-ASCII punctuation, streaming limits and session management—that make speech systems reliable in production.
10 years of coding experience
5 years of employment as a software developer
Bachelor of Science - BS, Data Science and Knowledge Engineering, Bachelor of Science - BS, Data Science and Knowledge Engineering at Maastricht UniversityDoctor of Philosophy - PhD, Machine Learning, Doctor of Philosophy - PhD, Machine Learning at Radboud UniversityMaster of Science - MS, Computer Science, Master of Science - MS, Computer Science at KTH Royal Institute of Technology
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (20)
xmpp10
python10
testing10
java10
sip10
javas10
sips10
speech-recognition10
jabber10
unit-testing9
360-video9
automatic-speech-recognition9
audio9
osgi9
test-automation9
Programming languages (13)
Github contributions (5)
jitsi/jiwer
Nov 2020 - Sep 2022
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
Role in this project:
QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:21 releases, 2 reviews, 24 commits in 1 year 9 months
Contributions summary:Nik's commits primarily focus on improving the testing and documentation of the `jiwer` library, which is designed for speech-to-text evaluation. They added tests for character error rate (CER) and fixed existing tests related to word error rate (WER) calculations. Their work included handling non-ASCII punctuation in the text transformations and fixing a bug in removing specific words, indicating a focus on test coverage and the robustness of the library's evaluation metrics.
ctcspeech-recognitionttserror-ratekaldi
jitsi/jigasi
Jul 2017 - Jan 2019
Jigasi: a server-side application acting as a gateway to Jitsi Meet conferences. Currently allows regular SIP clients to join meetings and provides transcription capabilities.
Role in this project:Back-end Developer
Back-end DeveloperContributions:1 review, 19 commits, 45 PRs in 1 year 5 months
Contributions summary:Nik primarily contributed to the development of the transcription feature within the Jigasi project, focusing on integrating the Google Cloud Speech-to-Text API. Their work involved implementing the transcription service, including audio processing and integration with the Google Cloud SDK. They addressed limitations of the API, such as the one-minute streaming restriction, by implementing a workaround. Furthermore, the user added local storage of transcriptions and improved session management for more real-time results.
actingjitsitranscriptionregulargateway
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.