A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Large-scale pretrained models for goal-directed dialog

PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

Official Pytorch implementation of ReXNet (Rank eXpansion Network) with pretrained models

PyTorch implementation of a collections of scalable Video Transformer Benchmarks.

A PyTorch implementation of the 'FaceNet' paper for training a facial recognition model with Triplet Loss using the glint360k dataset. A pre-trained model using Triplet Loss is available for download.

Real-time hand pose estimation and gesture classification using TensorRT

Image Synthesis + Corgis = <3

PyTorch implementation of "Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning" with DDP and Apex AMP

Mining Discourse Markers for Unsupervised Sentence Representation Learning

Code and released pre-trained model for our ACL 2022 paper: "DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation"

Source code of our SIGIR'24 paper titled "Leave No Patient Behind: Enhancing Medication Recommendation for Rare Disease Patients".

ALBERT trained on Mongolian text corpus

Custom YOLO11m model for detecting and classifying car body damage (99% shattered glass, 96% flat tire detection accuracy)—optimized for high-capacity inference and assistive use in inspection and service workflows like BMW pre-loaner inspections.

Forest Fire Detection By Convolutional Neural Network

This API utilizes a pre-trained model for emotion recognition from audio files. It accepts audio files as input, processes them using the pre-trained model, and returns the predicted emotion along with the confidence score. The API leverages the FastAPI framework for easy development and deployment.

Implemenation of Selective Kernel Networks by pytorch with pretrained weight

This is an implementation of electra according to the paper {ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators}

Custom YOLOv8 model for detecting and classifying car body damage—optimized for fast inference and assistive use in inspection and service workflows like BMW pre-loaner inspections.

Lane detection using tensorflow pre-trained model