mpc001 / auto_avsr

Visual Speech Recognition for Multiple Languages

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

Pytorch code for End-to-End Audiovisual Speech Recognition

Visual Speech Recognition for Multiple Languages

Terraform 是一种安全有效地构建、更改和版本控制基础设施的工具(基础架构自动化的编排工具)。它的目标是 "Write, Plan, and create Infrastructure as Code", 基础架构即代码。

#计算机科学#End-to-End Speech Processing Toolkit

#React UI#基于 Radix UI + Tailwind CSS 的UI库

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

Fairseq 是一个Python编写的 Seq2seq 建模工具包，可用于翻译、摘要、语言建模和其他文本生成任务训练自定义模型

Automated Lip reading from real-time videos in tensorflow in python

#计算机科学#🔓 Lip Reading - Cross Audio-Visual Recognition using 3D Architectures

Official Repository of the paper "Trajectory Consistency Distillation"

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

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

WACV 2020 "Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison"

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

#人脸识别#RetinaFace: Deep Face Detection Library for Python

Embed Python in Unreal Engine 4