Projects completed under Udacity's Natural Language Processing nanodegree program.
Project-1: Part of Speech Tagging
In this project we build a hidden Markov model for part of speech tagging with a universal tagset using the Pomegranate library.
Project-2: Machine Translation
In this project, we build a deep neural network that functions as part of a machine translation pipeline using Keras. The pipeline accepts English text as input and returns the French translation. The goal is to achieve the highest translation accuracy possible.
Project-3: Speech Recognizer
In this project we build deep neural networks using Keras that functions as part of an end-to-end automatic speech recognition (ASR) pipeline! The completed pipeline will accept raw audio as input and return a predicted transcription of the spoken language. In this capstone project, 5 RNN architectures are used and compared with each other.
Images credits: Flaticon