Starred repositories
Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection
Unified Schema-Based Information Extraction
Compute WER and SER for speech recognition evaluation
Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages
The /llms.txt file, helping language models use your website
🚀 The fast, Pythonic way to build MCP servers and clients.
Synthetic Dialog Generation and Analysis with LLMs
Time series distances: Dynamic Time Warping (fast DTW implementation in C)
Mapping the Media Landscape: Predicting Factual Reporting and Political Bias
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
On the Validity of Using the Therapist's prompts in Automatic Depression Detection from Clinical Interview
Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical Interviews
A library for mechanistic interpretability of GPT-style language models
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
An extremely fast Python package and project manager, written in Rust.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
🤗 smolagents: a barebones library for agents that think in code.
A high-throughput and memory-efficient inference and serving engine for LLMs
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Retrieval and Retrieval-augmented LLMs
DSPy: The framework for programming—not prompting—language models
Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis
Train transformer language models with reinforcement learning.
Fully open reproduction of DeepSeek-R1