Name: Wilfredo Martel
Type: User
Company: FullStack Developer | Semantic Search | NLP
Bio: I am a passionate student in Artificial Intelligence, specializing in semantic search, NLP, transformers, and bio-inspired algorithms.
Location: Ecuador
Blog: www.linkedin.com/in/wilfredomartel
Wilfredo Martel's Projects
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Code, datasets, and checkpoints for the paper "Improving Passage Retrieval with Zero-Shot Question Generation (EMNLP 2022)"
Learning to Detect Violent Videos using Convolution LSTM (Keras + tensorflow)
This repository will contain the code for the paper: "ViolenceNet: Dense Multi Head Self-Attention with Bidirectional Convolutional LSTM for detecting violence"
Violence detection in videos using Deep Learning (CNNs + LSTMs). 98.5% video accuracy and 97.81% frame level accuracy (with threshold=3) was achieved through the proposed model by Joshua on HockeyFight dataset. Joshua's project was extended with real-time predictions on video feed coming from camera. Moreover, notebook is added to easily setup and run code on Google Colab.
This project aims at classifying a video into a fight or non-fight video
Violence Detection using 3D Convolutional Neural Networks
A VoiceAsistant with WhisperAI speech recognition
I3D implemetation in Keras + video preprocessing (rgb and optical flows) to detect violence in videos with weak labels (Weakly Supervised) on XD-Violence dataset (Multi-Label, Multi-class and untrimmed videos) using Keras
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.
The frontend for ONLYOFFICE Document Server which builds the program interface
The frontend for ONLYOFFICE Document Server which builds the program interface
Automatically exported from code.google.com/p/webdav-msoffice-java
Robust Speech Recognition via Large-Scale Weak Supervision
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
Real time transcription with OpenAI Whisper.
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Multilingual abstractive summarization dataset extracted from WikiHow.
Experiments for XLM-V Transformers Integeration
question answer spanish
Topic-Aware Convolutional Neural Networks for Extreme Summarization