Luca Della Libera
Research Intern at Concordia University
Montreal, Quebec, Canada
Summary
🤩
Rockstar🎓
Top SchoolLuca Della Libera is a PhD student and research-focused software engineer based in Montreal with eight years of experience building and improving ML systems for speech and vision. He has interned at top research labs including Meta, Google DeepMind and Amazon, and currently contributes to SpeechBrain where he enhanced HuggingFace Whisper integration, fixed distributed training and multi-head attention, and refactored audio recipes. His background spans applied research roles (Huawei, BMW) and engineering positions (Motius), giving him a practical edge in taking models from experiments to robust code. At Concordia and Mila he focuses on speech processing research, while ongoing internships and industry collaborations keep his work grounded in production constraints. Notably, he implemented Mel spectrogram extraction in PyTorch and addressed backward compatibility in a major open-source speech toolkit—work that improves reproducibility and scalability for others. He combines rigorous academic training from TUM and Padova with hands-on contributions to high-impact open-source projects.
8 years of coding experience
2 years of employment as a software developer
Bachelor's degree, Information Engineering, 110 cum laude, Bachelor's degree, Information Engineering, 110 cum laude at Università degli Studi di PadovaHigh School Diploma, Mathematics, 100 cum laude, High School Diploma, Mathematics, 100 cum laude at Liceo Scientifico Galileo Galilei, Belluno, ItalySecondary School Diploma, 10, Secondary School Diploma, 10 at Scuola Secondaria Ippolito Nievo, Belluno, ItalyMaster's degree, Informatics, Passed with high distinction, Master's degree, Informatics, Passed with high distinction at Technical University of Munich
Italian, English, German
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (11)
transformers10
pytorch10
deeplearning-ai10
audio-processing10
deep-learning10
speech-processing10
asr9
python9
speech-recognition9
huggingface9
speech-to-text8
Programming languages (1)
Github contributions (5)
speechbrain/speechbrain
Nov 2022 - Nov 2022
A PyTorch-based Speech Toolkit
Role in this project:
ML Engineer
ML EngineerContributions:26 reviews, 1 commit, 19 PRs in 1 day
Contributions summary:Luca focused on enhancing the HuggingFace Whisper model within the SpeechBrain toolkit. Their work included extracting Mel spectrograms directly in PyTorch, addressing backward compatibility issues, and fixing distributed training and multi-head attention functionalities. They also refactored ESC50 recipes and added FocalNets, demonstrating expertise in integrating and improving speech processing models.
voice-recognitionasrspeech-recognitionspeech-separationspeaker-verification
lucadellalib/tensor-field-networks
Aug 2019 - Apr 2022
Contributions:6 commits, 6 pushes, 1 branch in 2 years 8 months
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.