toxtli / AutomEditor
AutomEditor is an AI based video editor that helps video bloggers to remove bloopers automatically. It uses multimodal spatio-temporal blooper recognition and localization approaches. The models were trained in keras and integrate feature fusion techniques from face, body gestures (skelethon), emotions progression, and audio features
☆47Updated 5 years ago
Alternatives and similar repositories for AutomEditor:
Users that are interested in AutomEditor are comparing it to the libraries listed below
- A Python Library for Multimodal Analysis of Movies and Content-based Movie Recommendation☆28Updated 3 years ago
- Automatically generate a lip-synced avatar based off of a transcript and audio☆14Updated last year
- This repository is a repository for the paper, "Irgun: Improved residue based gradual up-scaling network for single image super resolutio…☆12Updated 4 years ago
- Allows you to edit videos automatically☆43Updated 3 years ago
- Neural Voice Cloning with a few voice samples, using the speaker adaptation method. Speaker adaptation is based on fine-tuning a multi-sp…☆57Updated 5 years ago
- Final Project for Stanford Deep Generative Modeling Class CS236.☆14Updated 5 years ago
- A modified version of vid2vid for Speech2Video, Text2Video Paper☆35Updated last year
- You Said That?: Synthesising Talking Faces from Audio☆69Updated 6 years ago
- An automatic movie trailer generator.☆41Updated 2 years ago
- AI-generated talking head video of fake people responding to your input question text.☆69Updated 3 years ago
- Learning Lip Sync of Obama from Speech Audio☆67Updated 4 years ago
- Automatically generates TTS dataset using audio and associated text. Make cuts under a custom length. Uses Google Speech to text API to p…☆52Updated 2 years ago
- This is a phonemic multilingual (Russian-English) Implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-S…☆51Updated 4 years ago
- Deepstory turns a text/generated text into a video where the character is animated to speak your story using his/her voice.☆97Updated 2 years ago
- Emotional Speech Conversion using Style Transfer and MUNIT☆33Updated 5 years ago
- This repository is an implementation of Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis (SV2TTS) wit…☆168Updated 4 years ago
- Source for loopifi.com. Find and make smooth loops from videos! Create and download smoothly looping gifs and webms from youtube and othe…☆31Updated 2 years ago
- Generative voice cloning model using TTS synthesis with state-of-the-art Zero-Shot Multi-Speaker functionality. An web api built with the…☆47Updated 2 years ago
- TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction.☆88Updated 3 years ago
- A project that trains a neural network to recognize certain types of movie scenes (i.e: every drinking scene from Mad Men, every kissing …☆20Updated 2 years ago
- Unsupervised Any-to-many Audiovisual Synthesis via Exemplar Autoencoders☆120Updated 2 years ago
- This repository contains all the codes used in a thesis at Information Technology University (ITU). The topic of the thesis is pronunciat…☆25Updated 5 years ago
- Accompany code to reproduce the baselines of the International Multimodal Sentiment Analysis Challenge (MuSe 2020).☆16Updated 2 years ago
- Real-Time Lip Sync for Live 2D Animation☆135Updated 5 years ago
- [INTERSPEECH'2022] Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep Learning☆80Updated 2 years ago
- Predicting various emotion in human speech signal by detecting different speech components affected by human emotion.☆45Updated 5 months ago
- Project page for our paper "DurIAN : DurIAN-SC: Duration Informed Attention Network based Singing Voice Conversion System".☆10Updated 4 years ago
- Making an AI-generated music video from any song with Wav2CLIP and VQGAN-CLIP☆231Updated 2 years ago
- repo for active speaker detection for media videos.☆22Updated last year
- Create music videos using CLIP with BigGAN, DALL-E and StyleGAN☆54Updated 3 years ago