dariakryvosheieva/6.S058_lip_reading

Final project for MIT 6.S058: Introduction to Computer Vision

stars

commits

Python

primary language

May 14, 2025

updated

README

Enhancing Visual Speech Recognition with Language Models

By Sofia Dominguez (domingc7@mit.edu) and Daria Kryvosheieva (daria_k@mit.edu)

This project fine-tuned Auto-AVSR on two additional datasets (TCD-TIMIT + WildVSR) and experimented with integrating a language model into the beam search decoding process.

Contributors

dariakryvosheieva

5 commits

Similar repos

Kush5699/gujarati-vsr

aliencaocao/TIL-2023

Champion at Brainhack TIL 2023: Team 10000SGDMRT

AIRC-ASR/AIRC-ASR-Experimental

The experimental version of the project mostly used for protoyping different ideas.

FangyunWei/SLRT

389

umbertocappellazzo/Llama-AVSR

Official Pytorch implementation of "Large Language Models are Strong Audio-Visual Speech…

microsoft/SpeechT5

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing

1,450

SimoneMattioli98/Speech2Text

JeongHun0716/MMS-LLaMA

Official PyTorch implementation for "MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition…

Languages

Python

99.5%

README

Enhancing Visual Speech Recognition with Language Models

By Sofia Dominguez (domingc7@mit.edu) and Daria Kryvosheieva (daria_k@mit.edu)

This project fine-tuned Auto-AVSR on two additional datasets (TCD-TIMIT + WildVSR) and experimented with integrating a language model into the beam search decoding process.