Feb `18 – Dec `18
Zpoken Speech Recognition API
Machine Learning Engineer (Data scientist)
• Developing machine learning models using concepts of regression, random forest, boosting, GBM, NNs, HMMs, CRFs, MRFs, deep learning. • Developing several ready-to-use templates of machine learning models based on specifications given and assigned clear descriptions of purpose and variables given as input into the model. • Developing architecture around models for multi-task learning, distributed training on multiple machines, and integration into consumer-facing API
Zpoken STT (speech-to-text) engine – is a leading speech recognition software used for audio transcription, analytics, and voice-enabled applications. STT includes 5 different languages (English, Russian, Ukrainian, German and Chinese) that were developed from scratch and have accuracy more than 97%.
Technologies Stack:MongoDB Python Tableau Pig TensorFlow scikit-learn
Business & Productivity, Internet & Telecom, Data Science & Machine Learning, Big Data
AI- and NLP-driven language learning solution, Speech-to-text engine and handwritten chars generation