Minh Anh
AI Super Engineer at Speechify
Vietnam
Summary
🤩
Rockstar🎓
Top SchoolMinh Anh is an AI Super Engineer with 7 years of hands-on experience building and optimizing large-scale speech and generative models from research to production. Based in Vietnam, he leads multilingual, controllable TTS and voice conversion efforts at Speechify while pioneering self-supervised audio encoders, speech disentangling codecs, and flow-matching/GAN improvements for parallel models. A Kaggle Master and senior generative AI engineer, he is also the creator and main contributor to the TensorSpeech/TensorFlowTTS open-source framework, helping make state-of-the-art TTS accessible across languages. His background blends deep learning research with pragmatic engineering—real-time mobile TTS optimization, model quantization, and auto-compiler-driven training/inference acceleration—so he routinely bridges prototype research and production constraints. Notably, he has a strong math foundation from gifted-school training and applies that analytically to both model design and large-scale training pipelines.
7 years of coding experience
5 years of employment as a software developer
Mathematics, Mathematics at Thang Long high school for the gifted, Da Lat Province, Viet NamBachelor's degree Deep learing Machine Learning NLP, Bachelor's degree Deep learing Machine Learning NLP at Ho Chi Minh City University of Technology
Github Skills (7)
machine-learning10
deep-learning10
tensorflow10
modeling9
data-processing9
python9
trainings9
Programming languages (3)
Github contributions (5)
TensorSpeech/TensorFlowTTS
Mar 2020 - Mar 2022
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
Role in this project:
ML Engineer
ML EngineerContributions:7 releases, 60 reviews, 530 commits in 1 year 11 months
Contributions summary:Minh made several commits focused on initializing and updating the `setup.py` file, indicating a role in setting up the project. They also worked on the code that included modifying the dataset and model components. Their contributions include updates to the data processing pipeline, suggesting involvement in the training and/or deployment process of machine learning models within the project.
chinesesynthesisstuckspeech-recognitionstate-of-the-art
dathudeptrai/FastSpeech2
Jun 2020 - Aug 2020
Contributions:10 commits, 5 pushes, 1 branch in 1 month
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.