A RAG LLM co-pilot for browsing the web, powered by local LLMs

Transcribe desktop audio/computer audio in real-time and locally (Streaming ASR), using TorchAudio and Emformer-RNNT model for inference, PyAudio for reading stream, Tkinter for GUI.

An Open Source text-to-speech system built by inverting Whisper.

A Q&A platform software for teams at any scales. Whether it's a community forum, help center, or knowledge management platform, you can always count on Apache Answer.

Easily setup logical replication and switchover to new database with minimal downtime

JavaScript to Python Translator & JavaScript interpreter written in 100% pure Python🚀 Try it online:

Tools for merging pretrained large language models.

Mixtral finetuning

Listen to your users during product development with ClearFlask

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut …

Open Source realtime backend in 1 file

Reference implementation of Mistral AI 7B v0.1 model.

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Low cost, low effort P2P WebRTC serverless signalling using Cloudflare Workers

This is a list of speech tasks and datasets, which can provide training data for Generative AI, AIGC, AI model training, intelligent speech tool development, and speech applications.

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

A guidance language for controlling large language models.

C library for accessing the PostgreSQL parser outside of the server environment

[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score ru…

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

Label, clean and enrich text datasets with LLMs.

High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs

openai function calls for humans

Easy to use cryptographic framework for data protection: secure messaging with forward secrecy and secure data storage. Has unified APIs across 14 platforms.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

A collection of datasets for the purpose of emotion recognition/detection in speech.

Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"