Tech Stack
The Engineering Company for Digital Systems Development
Dec 2018 - Jun 2021 (2 years 7 months)
Machine Learning R&D
Responsibilities:
* Responsible to produce state-of-the-art speech recognition system with either a hybrid or end-to-end model
using Kaldi / TensorFlow / Docker.
* Contributing in different solutions in speech recognition, speech diarization and compute vision.
* Developing algorithms to solve critical problems within the production solution as a post-processing for our
developed model.
Projects:
● Hafss
Automatic verification of the correct pronunciation and narration of the Holy Quran verses.
Tech Stack: Kaldi, TensorFlow, Python.
● Voicea Cisco Webex
Speech recognition model for EVA "Virtual Intelligent Assistant" that's a part of Cisco Webex.
Tech Stack: Kaldi, python, Google Cloud Platform (PaaS).
● R
