Automated Speech Recognition

Created an ASR (Automatic Speech Recognition) system that takes in individual recordings. Each recording represents a sentence composed of 5-10 English language digits, separated by adequate pauses. The system involves segmenting the sentence using a classifier, differentiating between background and foreground sounds.

SPEAR-ASR and SPEAR-WakeUp Software Development Kit in Python for Linux

🧑🏻‍🎓 📑 October'20 - April'21. Group uni project. The project topic is Speech-to-Text Assessment Tool. It is a research-type project, most of the documentation is in a private GitLab repository.

ASR pytorch project

This is a Machine Learning project. This model takes video of person face as input and predicts the word. It uses tensorflow and keras for training the model. It uses Sequential models for trainning and predicting. It used relu and softmax as activation functions

The project,being part of Kagglex BIPOC Mentorship Program final project, aims to train two separate Hindi ASR models using the Facebook Wav2Vec2 (300M parameters) and OpenAI Whisper-Small models, respectively. The goal is to compare their performance, with a target WER of less than 13%, across various Hindi accents and dialects.

Test Repo

A Spotify Remote that operates using an ML Powered Automated Speech Recognization and Intent Detection Pipeline

557-Hours-Kazakh-Spontaneous-Speech-Data

Korean-Pronunciation-Dictionary

Burmese Spontaneous Speech Data

Indonesian conversational speech data

French Child's Spontaneous Speech Data

Dialect-Pronunciation-Dictionary

194999-Uyghur-Pronunciation-Dictionary

1044-Hours-Minnan-Dialect-Speech-Data-by-Mobile-Phone

Vietnamese-Spontaneous-Dialogue-Telephony-speech-dataset

Dockerfile for kaldi-gstreamer-server.