VSP-LLM

None

Stars: 275

Visit

VSP-LLM (Visual Speech Processing incorporated with LLMs) is a novel framework that maximizes context modeling ability by leveraging the power of LLMs. It performs multi-tasks of visual speech recognition and translation, where given instructions control the task type. The input video is mapped to the input latent space of a LLM using a self-supervised visual speech model. To address redundant information in input frames, a deduplication method is employed using visual speech units. VSP-LLM utilizes Low Rank Adaptors (LoRA) for computationally efficient training.

README:

VSP-LLM (Visual Speech Processing incorporated with LLMs)

This is the PyTorch code for Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing. This code is developed on the code of AV-HuBERT.

Introduction

We propose a novel framework, namely Visual Speech Processing incorporated with LLMs (VSP-LLM), to maximize the context modeling ability by bringing the overwhelming power of LLMs. Specifically, VSP-LLM is designed to perform multi-tasks of visual speech recognition and translation, where the given instructions control the type of task. The input video is mapped to the input latent space of a LLM by employing a self-supervised visual speech model. Focused on the fact that there is redundant information in input frames, we propose a novel deduplication method that reduces the embedded visual features by employing visual speech units. Through the proposed deduplication and Low Rank Adaptors (LoRA), VSP-LLM can be trained in a computationally efficient manner.

Model checkpoint

You can find checkpoint of our model in here. Move the checkpoint to checkpoints.

Preparation

conda create -n vsp-llm python=3.9 -y
conda activate vsp-llm
git clone https://github.com/Sally-SH/VSP-LLM.git
cd VSP-LLM
pip install -r requirements.txt
cd fairseq
pip install --editable ./

Download AV-HuBERT pre-trained model AV-HuBERT Large (LSR3 + VoxCeleb2) from here.
Download LLaMA2-7B from here.

Move the AV-HuBERT pre-trained model checkpoint and the LLaMA2-7B checkpoint to checkpoints.

Data preprocessing

Follow Auto-AVSR preparation to preprocess the LRS3 dataset.
Then, follow AV-HuBERT preparation from step 3 to create manifest of LRS3 dataset.

Generate visual speech unit and cluster counts file

Follow the steps in clustering to create:

{train,valid}.km frame-aligned pseudo label files. The label_rate is the same as the feature frame rate used for clustering, which is 25Hz for AV-HuBERT features by default.

Dataset layout

.
├── lrs3
│     ├── lrs3_video_seg24s               # Preprocessed video and audio data
│     └── lrs3_text_seg24s                # Preprocessed text data
├── muavic_dataset                        # Mix of VSR data and VST(En-X) data
│     ├── train.tsv                       # List of audio and video path for training
│     ├── train.wrd                       # List of target label for training
│     ├── train.cluster_counts            # List of clusters to deduplicate speech units in training
│     ├── test.tsv                        # List of audio and video path for testing
│     ├── test.wrd                        # List of target label for testing
│     └── test.cluster_counts             # List of clusters to deduplicate speech units in testing
└── test_data
      ├── vsr
      │    └── en
      │        ├── test.tsv 
      │        ├── test.wrd  
      │        └── test.cluster_counts           
      └── vst
           └── en
               ├── es
               :   ├── test.tsv
               :   ├── test.wrd 
               :   └── test.cluster_counts
               └── pt
                   ├── test.tsv
                   ├── test.wrd 
                   └── test.cluster_counts

Test data

The test manifest is provided in labels. You need to replace the path of the LRS3 in the manifest file with your preprocessed LRS3 dataset path using the following command:

cd src/dataset
python replace_path.py --lrs3 /path/to/lrs3

Then modified test amanifest is saved in dataset

Training

Open the training script (scripts/train.sh) and replace these variables:

# path to train dataset dir
DATA_PATH=???

# path where output trained models will be located
OUT_PATH=???

Run the training script:

$ bash scripts/train.sh

Decoding

Open the decoding script (scripts/decode.sh) and replace these variables:

# language direction (e.g 'en' for VSR task / 'en-es' for En to Es VST task)
LANG=???

# path to the trained model
MODEL_PATH=???

# path where decoding results and scores will be located
OUT_PATH=???

Run the decoding script:

$ bash scripts/decode.sh

For Tasks:

Click tags to check more tools for each tasks

recognize speech from videos translate speech from one language to another generate captions for videos create lip-sync animations control virtual characters with speech

For Jobs:

speech recognition engineer machine learning engineer data scientist research scientist software engineer

Alternative AI tools for VSP-LLM

Similar Open Source Tools

VSP-LLM

github

: 275

HebTTS

HebTTS is a language modeling approach to diacritic-free Hebrew text-to-speech (TTS) system. It addresses the challenge of accurately mapping text to speech in Hebrew by proposing a language model that operates on discrete speech representations and is conditioned on a word-piece tokenizer. The system is optimized using weakly supervised recordings and outperforms diacritic-based Hebrew TTS systems in terms of content preservation and naturalness of generated speech.

github

: 52

ontogpt

OntoGPT is a Python package for extracting structured information from text using large language models, instruction prompts, and ontology-based grounding. It provides a command line interface and a minimal web app for easy usage. The tool has been evaluated on test data and is used in related projects like TALISMAN for gene set analysis. OntoGPT enables users to extract information from text by specifying relevant terms and provides the extracted objects as output.

github

: 584

BTGenBot

BTGenBot is a tool that generates behavior trees for robots using lightweight large language models (LLMs) with a maximum of 7 billion parameters. It fine-tunes on a specific dataset, compares multiple LLMs, and evaluates generated behavior trees using various methods. The tool demonstrates the potential of LLMs with a limited number of parameters in creating effective and efficient robot behaviors.

github

: 65

VideoTree

VideoTree is an official implementation for a query-adaptive and hierarchical framework for understanding long videos with LLMs. It dynamically extracts query-related information from input videos and builds a tree-based video representation for LLM reasoning. The tool requires Python 3.8 or above and leverages models like LaViLa and EVA-CLIP-8B for feature extraction. It also provides scripts for tasks like Adaptive Breath Expansion, Relevance-based Depth Expansion, and LLM Reasoning. The codebase is being updated to incorporate scripts/captions for NeXT-QA and IntentQA in the future.

github

: 94

MPLSandbox

MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for LLMs. It simplifies code analysis for researchers and can be seamlessly integrated into LLM training and application processes to enhance performance in a range of code-related tasks. The sandbox environment ensures safe code execution, the code analysis module offers comprehensive analysis reports, and the information integration module combines compilation feedback and analysis results for complex code-related tasks.

github

: 174

VoiceStreamAI

VoiceStreamAI is a Python 3-based server and JavaScript client solution for near-realtime audio streaming and transcription using WebSocket. It employs Huggingface's Voice Activity Detection (VAD) and OpenAI's Whisper model for accurate speech recognition. The system features real-time audio streaming, modular design for easy integration of VAD and ASR technologies, customizable audio chunk processing strategies, support for multilingual transcription, and secure sockets support. It uses a factory and strategy pattern implementation for flexible component management and provides a unit testing framework for robust development.

github

: 547

KrillinAI

KrillinAI is a video subtitle translation and dubbing tool based on AI large models, featuring speech recognition, intelligent sentence segmentation, professional translation, and one-click deployment of the entire process. It provides a one-stop workflow from video downloading to the final product, empowering cross-language cultural communication with AI. The tool supports multiple languages for input and translation, integrates features like automatic dependency installation, video downloading from platforms like YouTube and Bilibili, high-speed subtitle recognition, intelligent subtitle segmentation and alignment, custom vocabulary replacement, professional-level translation engine, and diverse external service selection for speech and large model services.

github

: 655

POPPER

Popper is an agentic framework for automated validation of free-form hypotheses using Large Language Models (LLMs). It follows Karl Popper's principle of falsification and designs falsification experiments to validate hypotheses. Popper ensures strict Type-I error control and actively gathers evidence from diverse observations. It delivers robust error control, high power, and scalability across various domains like biology, economics, and sociology. Compared to human scientists, Popper achieves comparable performance in validating complex biological hypotheses while reducing time by 10 folds, providing a scalable, rigorous solution for hypothesis validation.

github

: 123

llm-random

This repository contains code for research conducted by the LLM-Random research group at IDEAS NCBR in Warsaw, Poland. The group focuses on developing and using this repository to conduct research. For more information about the group and its research, refer to their blog, llm-random.github.io.

github

: 181

Magic_Words

Magic_Words is a repository containing code for the paper 'What's the Magic Word? A Control Theory of LLM Prompting'. It implements greedy back generation and greedy coordinate gradient (GCG) to find optimal control prompts (magic words). Users can set up a virtual environment, install the package and dependencies, and run example scripts for pointwise control and optimizing prompts for datasets. The repository provides scripts for finding optimal control prompts for question-answer pairs and dataset optimization using the GCG algorithm.

github

: 61

storm

STORM is a LLM system that writes Wikipedia-like articles from scratch based on Internet search. While the system cannot produce publication-ready articles that often require a significant number of edits, experienced Wikipedia editors have found it helpful in their pre-writing stage. **Try out our [live research preview](https://storm.genie.stanford.edu/) to see how STORM can help your knowledge exploration journey and please provide feedback to help us improve the system 🙏!**

github

: 17.0k

renumics-rag

Renumics RAG is a retrieval-augmented generation assistant demo that utilizes LangChain and Streamlit. It provides a tool for indexing documents and answering questions based on the indexed data. Users can explore and visualize RAG data, configure OpenAI and Hugging Face models, and interactively explore questions and document snippets. The tool supports GPU and CPU setups, offers a command-line interface for retrieving and answering questions, and includes a web application for easy access. It also allows users to customize retrieval settings, embeddings models, and database creation. Renumics RAG is designed to enhance the question-answering process by leveraging indexed documents and providing detailed answers with sources.

github

: 155

gaussian-painters

This tool is a fork of the 3D Gaussian Splatting code. It allows users to create a dataset ready to be trained with the Gaussian Splatting code. The dataset can be used for various experiments, such as creating orthogonal images, steganography, and lenticular effects. The tool also includes a visualizer that allows users to visualize the "painting" process during the Gaussian Splatting optimization.

github

: 358

cookiecutter-data-science

Cookiecutter Data Science (CCDS) is a tool for setting up a data science project template that incorporates best practices. It provides a logical, reasonably standardized but flexible project structure for doing and sharing data science work. The tool helps users to easily start new data science projects with a well-organized directory structure, including folders for data, models, notebooks, reports, and more. By following the project template created by CCDS, users can streamline their data science workflow and ensure consistency across projects.

github

: 8.7k

cover-agent

CodiumAI Cover Agent is a tool designed to help increase code coverage by automatically generating qualified tests to enhance existing test suites. It utilizes Generative AI to streamline development workflows and is part of a suite of utilities aimed at automating the creation of unit tests for software projects. The system includes components like Test Runner, Coverage Parser, Prompt Builder, and AI Caller to simplify and expedite the testing process, ensuring high-quality software development. Cover Agent can be run via a terminal and is planned to be integrated into popular CI platforms. The tool outputs debug files locally, such as generated_prompt.md, run.log, and test_results.html, providing detailed information on generated tests and their status. It supports multiple LLMs and allows users to specify the model to use for test generation.

github

: 4.2k

For similar tasks

VSP-LLM

github

: 275

For similar jobs

weave

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

github

: 855

agentcloud

AgentCloud is an open-source platform that enables companies to build and deploy private LLM chat apps, empowering teams to securely interact with their data. It comprises three main components: Agent Backend, Webapp, and Vector Proxy. To run this project locally, clone the repository, install Docker, and start the services. The project is licensed under the GNU Affero General Public License, version 3 only. Contributions and feedback are welcome from the community.

github

: 583

oss-fuzz-gen

This framework generates fuzz targets for real-world `C`/`C++` projects with various Large Language Models (LLM) and benchmarks them via the `OSS-Fuzz` platform. It manages to successfully leverage LLMs to generate valid fuzz targets (which generate non-zero coverage increase) for 160 C/C++ projects. The maximum line coverage increase is 29% from the existing human-written targets.

github

: 1.2k

LLMStack

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

github

: 1.5k

VisionCraft

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

github

: 94

kaito

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

github

: 405

PyRIT

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

github

: 2.3k

Azure-Analytics-and-AI-Engagement

The Azure-Analytics-and-AI-Engagement repository provides packaged Industry Scenario DREAM Demos with ARM templates (Containing a demo web application, Power BI reports, Synapse resources, AML Notebooks etc.) that can be deployed in a customer’s subscription using the CAPE tool within a matter of few hours. Partners can also deploy DREAM Demos in their own subscriptions using DPoC.

github

: 136