Raj Gothi's repositories
Improving-Automatic-Speech-Recognition-with-Dialect-Specific-Language-Models
This repository contains the implementation of our published paper titled 'Improving Automatic Speech Recognition with Dialect-Specific Language Models,' presented at SPECOM'23.
Visual-Entities-Empowered-Zero-Shot-Image-to-Text-Generation-Transfer-Across-Domains
Visual Entities Empowered Zero-Shot Image-to-Text Generation Transfer Across Domains
City-Inhabitant-Term-Prediction--T5-Model
To create a predictive model that, when provided with the name of a city, can generate the corresponding term used to describe its inhabitants, such as "Mumbai" -> "Mumbaikar."
CS753-imputer-Automatic-Speech-Recognition-ASR
Implementation of Imputer: Sequence Modelling via Imputation and Dynamic Programming in PyTorch
GPT-from-scratch
Pre-train the dataset of Shakespeare poem to make character level language model using decoder only transformer.
Multi-Document-Summarization
Machine Learning and Natural Language Processing
NLP-and-Speech-Hugging-Face
It includes various NLP and speech tasks using the Hugging Face and PyTorch libraries.
silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector, Language Classifier and Spoken Number Detector
Web_Crawling
It crawl the website https://newsonair.gov.in/RNU-NSD-AudioTo download the audio and transcript corresponding to given field value.