#
Lists (1)
Starred repositories
Vi_G2P or ViG2P: G2P package for Vietnamese: based on vPhon and phonology knowledge to convert Raw text - Graphoneme to IPA
A unified tokenizer that is capable of both extracting semantic information and enabling high-fidelity audio reconstruction.
Best practices & guides on how to write distributed pytorch training code
[ICASSP 2024] KNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
AI-powered tool that transforms STEM concepts into narrated educational animations using Manim, LLMs, and multimodal AI
Suite of tools to discover new articles on the arXiv, filter them, and broadcast them as an RSS feed, for your own use or for others.
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding a…
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
A high-throughput and memory-efficient inference and serving engine for LLMs
An Open-Source Asynchronous Coding Agent
Tips and resources to prepare for Behavioral interviews.
The python library for real-time communication
Memory efficient transducer loss computation
Hierarchical Reasoning Model Official Release
A python package to analyze and compare voices with deep learning
[ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Computation-Efficient Era: A Comprehensive Survey of State Space Models in Medical Image Analysis
ViStreamASR - Real-Time Vietnamese Speech Recognition
Code for the paper "Instituto de Telecomunicações at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning"
Web interface for browsing, search and filtering recent arxiv submissions
PyTorch code and models for V-JEPA self-supervised learning from video.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.