Eren Gölge
Chief Architect Of Voice Products at Cantina
Germany
Summary
🤩
Rockstar🎓
Top SchoolEren Gölge is a Chief Architect of Voice Products based in Germany with 13 years of experience building production-grade AI/ML systems, particularly in text-to-speech and speech synthesis. As a co-founder and former Head of AI at Coqui and an early creator of Mozilla TTS, he has led ML and data teams, designed controllable TTS models like XTTS/YourTTS, and driven major open-source projects used across languages. His hands-on work spans model design, performance optimization (e.g., Tacotron2 tf.function optimizations), vocoder benchmarking, and backend model engineering, reflecting deep expertise from research to productization. He combines startup grit—founding and exiting an earlier company—with academic rigor from Bilkent University, and a knack for turning messy research problems into robust, community-driven code. An uncommon strength is his focus on both low-level performance fixes and community-facing documentation, ensuring models are fast, reproducible, and widely adoptable.
13 years of coding experience
10 years of employment as a software developer
Bachelor of Science (BS) Computer Science, Bachelor of Science (BS) Computer Science at Bilkent UniversityAnkara Ataturk Anadolu Lisesi
English, German
Stackoverflow
13,426reputation
1.9mreached
42answers
279questions
Github Skills (22)
pytorch10
python10
attention-mechanism10
machine-learning10
text-to-speech10
speech-synthesis10
deep-learning10
tensorflow10
taco10
neural-network10
documentation10
speech-to-text9
rnn-model8
n8
mlops7
Programming languages (11)
Github contributions (5)
coqui-ai/TTS
Jan 2021 - Jan 2023
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Role in this project:
Backend Developer
Backend DeveloperContributions:99 releases, 297 reviews, 1516 commits in 2 years
Contributions summary:Eren implemented updates to the `speedy_speech.py` model, suggesting work in deep learning model development. They made changes to model layers and updated tests, indicating responsibilities in modifying and testing the model architecture. The user's actions likely involved improving the training pipeline and performance of the models.
text-to-speechpythonspeaker-encodingsasrglow-tts
mozilla/TTS
Jan 2018 - Feb 2021
:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
Role in this project:Full-stack Developer
Full-stack DeveloperContributions:1 release, 45 reviews, 806 commits in 3 years 1 month
Contributions summary:Eren's commits primarily focused on documentation, specifically detailing the usage of notebook for creating and benchmarking a ParallelWaveGAN vocoder. The user also made improvements to the code quality by running pylint checks and fixing linter issues. Furthermore, the commits introduced a new function, further indicating their involvement in implementing and documenting components related to the Text-to-Speech framework.
balloonpythondataset-analysisglow-ttsspeech-recognition
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.