Rudrabha Mukhopadhyay

Clean-Subtitles. A simple way to generate SRT files with customizable lengths and characters.

FramePack. Lets make video diffusion practical!

UniAnimate-DiT. UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer

VACE. [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

SkyReels-V1. SkyReels V1: The first and most advanced open-source human-centric video foundation model

resemble-enhance. AI powered speech denoising and enhancement

gestsync. Official code for the paper "GestSync: Determining who is speaking without a talking head" published at BMVC 2023

Wav2Lip-PyTorch-To-CoreML. A guide for converting the Wav2Lip PyTorch model to CoreML using ONNX for deployment in iOS applications.

VDT. [ICLR2024] The official implementation of paper "VDT: General-purpose Video Diffusion Transformers via Mask Modeling", by Haoyu Lu, Guoxing Yang, Nanyi Fei, Yuqi Huo, Zhiwu Lu, Ping Luo, Mingyu Ding.

Devon. Devon: An open-source pair programmer

quary. Open-source BI for engineers

magic_animate_unofficial. An unoffical training code of Magic Animate

Wav2Lip. This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

movie-asd. repo for active speaker detection for media videos.

UniFormerV2. [ICCV2023] UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer

pix2seq. Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

MMVAE-AVS. Multimodal Variational Auto-encoder based Audio-Visual Segmentation [ICCV2023].

itsabouttime. Code repository for "It's About Time: Analog clock Reading in the Wild"

ImageBind. ImageBind One Embedding Space to Bind Them All

Lip-to-Speech-Synthesis-in-the-Wild. PyTorch implementation of "Lip to Speech Synthesis in the Wild with Multi-task Learning" (ICASSP2023)

video-retalking. [SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

FastGAN-pytorch. Official implementation of the paper "Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis" in ICLR 2021

ProDiff. PyTorch Implementation of ProDiff (ACM-MM'22) with a Extremely-Fast diffusion speech synthesis pipeline

speech-transformer. Transformer implementation speciaized in speech recognition tasks using Pytorch.

CodeFormer. [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

awesome-talking-head-generation.

awesome-zero-knowledge-proofs. A curated list of awesome things related to learning Zero-Knowledge Proofs (ZKP).

style-transformer. Official implementation for "Style Transformer for Image Inversion and Editing" (CVPR 2022)

transpotter. Official implementation of Transpotter, published in BMVC 2021

Face-Hallucination-Benchmark. A collection of state-of-the-art face super-resolution/hallucination methods

LIA. [ICLR 22, TPAMI 24] LIA: Latent Image Animator

rgbd_streamer. Python

project-walkthroughs. Data science, machine learning, and web development project code for https://www.youtube.com/c/Dataquestio .

3DMM-Fitting-Pytorch. A 3DMM fitting framework using Pytorch.

STIT. Python

High-Resolution-Neural-Face-Swapping-for-Visual-Effects. High-Resolution Neural Face Swapping for Visual Effects

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

mediapipe_pytorch. PyTorch implementation of Google's Mediapipe model. Iris Landmark model | Face Mesh Model

CNAK. Cluster number assisted K-means

DeepImageBlending. This is a Pytorch implementation of deep image blending

docformer. Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU)

Towards-Automatic-Speech-to-SL. Python

deep_avsr. A PyTorch implementation of the Deep Audio-Visual Speech Recognition paper.

Peregrine. A blazing fast language for the blazing fast world(WIP)

motion-cosegmentation. Reference code for "Motion-supervised Co-Part Segmentation" paper

Machine-Translation-Transformers. Python

VideoGPT. Jupyter Notebook

Lipreading_using_Temporal_Convolutional_Networks. ICASSP'22 Training Strategies for Improved Lip-Reading; ICASSP'21 Towards Practical Lipreading with Distilled and Efficient Models; ICASSP'20 Lipreading using Temporal Convolutional Networks

taming-transformers. Taming Transformers for High-Resolution Image Synthesis

nerfies. This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.

python-sounddevice. :sound: Play and Record Sound with Python :snake:

DECA. DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

gdrive. Google Drive CLI Client

alias-free-gan. Alias-Free GAN project website and code

wav2lip-hq. Extension of Wav2Lip repository for processing high-quality videos.

Torch-Pruning. [CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

perceiver-pytorch. Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

playground. useful code samples

KWS-Net. Seeing Wake Words: Audio-visual Keyword Spotting

langid.py. Stand-alone language identification system

peoples-speech. The People’s Speech Dataset

HDTF. the dataset and code for "Flow-guided One-shot Talking Face Generation with a High-resolution Audio-visual Dataset"

slt_base. Python

stochastic-gates. Codebase for "Channel selection using Gumbel Softmax"

NR-GAN. NR-GAN: Noise Robust Generative Adversarial Networks

PhraseCutDataset. Dataset API for "PhraseCut: Language-based Image Segmentation in the Wild"

BRIMs. Implementation of Bidirectional Recurrent Independent Mechanisms (Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules)

Talking-Face_PC-AVS. Code for Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)

articulated-animation. Code for Motion Representations for Articulated Animation paper

learn-an-effective-lip-reading-model-without-pains. The PyTorch Code and Model In "Learn an Effective Lip Reading Model without Pains", (https://arxiv.org/abs/2011.07557), which reaches the state-of-art performance in LRW-1000 dataset.

you_said_that. Python

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

self-attention-cv. Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository.

vilbert-multi-task. Multi Task Vision and Language

ECANet. Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

end2end-asr-pytorch. End-to-End Automatic Speech Recognition on PyTorch

MultiTune. Adaptive Integration of Multiple Fine-tuning Models in Transfer Learning for Image Classification

decord. An efficient video loader for deep learning with smart shuffling that's super easy to digest

SpeechSplit. Unsupervised Speech Decomposition Via Triple Information Bottleneck

rir_simulator_python. Room impulse response simulator using python

TimeSformer-pytorch. Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification

pydub. Manipulate audio with a simple and easy high level interface

PythonAudioEffects. A Python library that can apply: darth vader, echo, radio, robotic, and ghost effects to audio samples.

conformer. [Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

Deep-Iterative-Collaboration. Pytorch implementation of Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation (CVPR 2020)

Face-SPARNet. Pytorch codes for "Learning Spatial Attention for Face Super-Resolution", TIP 2021.

face-alignment. :fire: 2D and 3D Face alignment library build using pytorch

image-captioning-DLCT. Official pytorch implementation of paper "Dual-Level Collaborative Transformer for Image Captioning" (AAAI 2021).

Word-recognition-EmbedNet-CAB. Code implementation for our ICPR, 2020 paper titled "Improving Word Recognition using Multiple Hypotheses and Deep Embeddings"

audio_gui. Simple audio recorder that sends WAV from browser to server in Python (Flask).

melgan. MelGAN vocoder (compatible with NVIDIA/tacotron2)

MelGAN-Pytorch. A Pytorch Implementation of MelGAN

image-gpt. Python

Machine-Learning-Collection. A resource for learning about Machine learning & Deep Learning

CADA-VAE-PyTorch. Official implementation of the paper "Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders" (CVPR 2019)

Video-Action-Transformer-Network-Pytorch-. Implementation of the paper Video Action Transformer Network

ctci-python-solutions. Cracking the Coding Interview in Python 3. The solutions all have detailed explanations with visuals.

Summer2026-Internships. Summer 2026 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC.

impersonator. PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

complexPyTorch. A high-level toolbox for using complex valued neural networks in PyTorch

ComplexCNN. pytorch implementation of complex convolutional neural network

pseudo-visual-speech-denoising. Official code for the paper "Visual Speech Enhancement Without A Real Visual Stream" published at WACV 2021

lip2wav_revised. Revision and tools of lip2wav

SpeakingFaces. A large-scale publicly-available visual-thermal-audio dataset designed to encourage research in the general areas of user authentication, facial recognition, speech recognition, and human-computer interaction.

DeepSpeechDistances. Authors' implementation of DeepSpeech Distances.

melgan-neurips. GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

WatermarkNN. Watermarking Deep Neural Networks (USENIX 2018)

B-Plus-Tree. Mini Database System using B+ Tree in C++ (Simple & Self-Explanatory Code)

Transformer-TTS. A Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"

Cone-of-Silence. The Cone of Silence:

SpeechDenoisingWithDeepFeatureLosses. Speech Denoising with Deep Feature Losses

segan. Speech Enhancement Generative Adversarial Network in TensorFlow

3DDFA_V2. The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

3DDFA. The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

QUT-NOISE. The QUT-NOISE database and protocols

summarize-from-feedback. Code for "Learning to summarize from human feedback"

RAFT. Python

minGPT. A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

av-se. Deep-Learning-Based Audio-Visual Speech Enhancement and Separation

DIP-Monsoon2019-Project. DIP-Monsoon2019-Project

AutoVPN. This is an automatic VPN installer-runner for IIIT-H students.

python-knowledge-graph. A Python implementation of a basic Knowledge Graph

GettingToKnowYou. Python

character-mining. Mining individual characters in multiparty dialogue

VideoStreamingFlask. Streaming video with the help of Flask and Opencv

awesome-deepfakes-materials. A curated list of awesome Deepfakes materials

3d-photo-inpainting. [CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

awesome-egocentric-vision. A curated list of egocentric (first-person) vision and related area resources

speech-driven-animation. Python

Audio-driven-TalkingFace-HeadPose. Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose" (Arxiv 2020) and "Predicting Personalized Head Movement From Short Video and Speech Signal" (TMM 2022)

identity-cloning-toolkit-ICT. This project has all the components which you can use to clone yourself over digital channel

pytorch-fid. Compute FID scores with PyTorch.

pytorch-frechet-inception-distance. A Pytorch Implementation of the Fréchet Inception Distance (FID)

keras-fid. Frechet Inception Distance for Keras-based GANs

metrics. IS, FID score Pytorch and TF implementation, TF implementation is a wrapper of the official ones.

syncnet_trainer. Disentangled Speech Embeddings using Cross-Modal Self-Supervision

syncnet_python. Out of time: automated lip sync in the wild

Talking-head-Generation-with-Rhythmic-Head-Motion. Python

deep_lip_reading. Code and models for evaluating a state-of-the-art lip reading network

multisensory. Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

audino. Open source audio annotation tool for humans

dogsVScats. Kaggle Cats vs. Dogs Redux Edition

detr. End-to-End Object Detection with Transformers

context_rank. Semantyc is a contextual mobile search engine that is user/ "People" centric and returns results to queries which is relevent and personalized to the user and is based on the meaning of the query of the user rather than the keywords in the query.

Pegasos_SVM. Course Project for Optimization Methods (CS481) at IIIT Hyderabad

Word-recognition-and-retrieval. Code implementation for our DAS, 2020 paper titled "Fused Text Recogniser and Deep Embeddings Improve Word Recognition and Retrieval"

dataset_agnostic_segmentation. TensorFlow implementation of a segmentation system for document images.

Speaker_Verification. Tensorflow implementation of "Generalized End-to-End Loss for Speaker Verification"

Real-Time-Voice-Cloning. Clone a voice in 5 seconds to generate arbitrary speech in real-time

generative-query-network-pytorch. Generative Query Network (GQN) in PyTorch as described in "Neural Scene Representation and Rendering"