Himanshu Maurya's repositories
speech-editor
A streamlit based UI for editing speech
Transformer-Stance-Detection
This is a transformer based implementation for Stance Detection with Bidirectional Conditional Encoding
cross-text-PT
Improving the Appropriateness in Cross-Text Prosody Transfer using Human Supervision
corise-recsys-at-scale
Project files from Corise Recsys at Scale course
fs2-server
FastAPI server for synthesizing speech using FastSpeech2
lordzuko.github.io
lordzuko's personal website and blog
SpeakingStyle
Aligning latent space of speaking style with human perception using a re-embedding strategy
intent-classification
A multilingual intent classficiation service
lordzuko_sb
Building my second brain
probabilistic-deep-learning
Code for various probabilistic deep learning models
datatrove
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
deep-learning-for-audio-processing
Deep learning for audio processing
EffectivePyTorch
PyTorch tutorials and best practices.
FastSpeech2
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
FastSpeech2-jax
Implementation of FastSpeech2 in JAX
github-readme-stats
:zap: Dynamically generated stats for your github readmes
hifi-gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
llama
Inference code for LLaMA models
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
LLMUnity
Create characters in Unity with LLMs!
Machine-Learning-Interviews
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
speaking-style-survey
Speech samples to be used as part of qualtrics survey for speech for perception alignment of speaking style project
udacity-projects
Collections of udacity projects from various nanodegrees