Aashish Yadavally's repositories
Hindi-Speech-Corpus
A short-vocabulary Hindi speech corpus with phonological and acoustic analysis for Automatic Speech Recognition
Working-with-Kaldi
Here, I updated the projects that I have worked on in Automatic Speech Recognition using the Kaldi Toolkit. They can be found in the 'egs' folder in the following format: <Project Number>_MP_<Project>
aws-data-etl
A data ETL pipeline built using AWS tools such as S3, ElasticMapReduce (EMR) and RedShift.
bruce
Cilia Segmentation
einstein
Solar Irradiance Prediction using PySpark
hopper
Code Neuro Finding Challenge
Malware-Classification
Malware Classification
Multi-Label-Classification
Multi label classification of Arxiv Abstracts
NLP-using-Spark
Data Science Practicum : Project 0
Regression-in-ScalaTion-and-R
Regression Problem in Scalation and R
Speaker-Recognition
A speaker recognition system using the MFCC features and ANN for feature extraction. The system has been trained and tested on the CHAINS dataset.
tensorflow-pickup-lines
A pickup line generator using Tensorflow
xwordgen
Word Level Text Generation using Neural and Statistical Language Models