Alistair Walsh's repositories
VoiceCraft
Zero-Shot Speech Editing and Text-to-Speech in the Wild
alpaca-lora
Instruct-tune LLaMA on consumer hardware
AudioGPT
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
automl-app
AutoML Web App - build Machine Learning pipeline in automatic way with Graphical User Interface (GUI). You can run app locally!
chat-with-data
A repository to Chat with Data (Csv, Excel)
civic-agentcy
Public policy multi-agent research with CrewAI
ComfyUI-to-Python-Extension
A powerful tool that translates ComfyUI workflows into executable Python code.
DeepSpeech
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
demucs
Code for the paper Hybrid Spectrogram and Waveform Source Separation
Digital_Insurgency
a cyberpunk novella
dspy
DSPy: The framework for programming—not prompting—foundation models
freemocap
Free Motion Capture for Everyone 💀✨
gazelle
Joint speech-language model - respond directly to audio!
jupyter-ai
jupyter-ai lab in streamlit
langchain
⚡ Building applications with LLMs through composability ⚡
lmql
A language for constraint-guided and efficient LLM programming.
Mora
Mora: More like Sora for Generalist Video Generation
pyannote-audio
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
raspi_crew
Setup for crewai on raspi4
sd-webui-chatgpt
This is a repository for using ChatGPT in Stable Diffusion web UI.
so-vits-svc-fork
so-vits-svc fork with realtime support, improved interface and more features.
stable-diffusion-webui-docker
Easy Docker setup for Stable Diffusion with user-friendly UI
streamlit-agent
Reference implementations of several LangChain agents as Streamlit apps
streamlit-option-menu
streamlit-option-menu is a simple Streamlit component that allows users to select a single item from a list of options in a menu.
TalkWithYourFiles
An LLM GUI application; enables you to interact with your files, offering dynamic parameters that can modify response behavior during runtime.