Feiteng

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

Omni SenseVoice: High-Speed Speech Recognition with words timestamps 🗣️🎯

Cross-platform VAD & Audio Event Detection toolkit — Python (PyPI) + TypeScript (npm) + C API. DFSMN models ~2MB, 200x real-time. Runs everywhere: native, browser (WASM), Node.js.

FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3

Tech

No description.

Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark

Text-To-Speech for NotebookLM

Faster Deep Neural Networks

No description.

TTS Text Analyzer

solutions for https://www.kaggle.com/c/tensorflow-speech-recognition-challenge

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

Explore Text-To-Speech

Tensorflow Optimizers

五行代码实现一个SVM

Topics in Automatic Speech Recognition

No description.

A library built for easier audio self-supervised training, downstream tasks evaluation

Tools for handling speech data in machine learning projects.

Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

No description.

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice

Hanzi Converter for Traditional and Simplified Chinese

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

A timeline of the latest AI models for audio generation, starting in 2023!

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Grapheme to phoneme conversion with deep learning.

Awesome Audio Skills for Claude & Antigravity: A curated list of tools, MCP servers, and scripts to handle audio streams, convert formats, and extract intelligence from speech using Claude's reasoning capabilities.

Prediction of sound event bounding boxes (SEBBs)

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

Wan: Open and Advanced Large-Scale Video Generative Models

Distributed Coordinated Sequence Sampler

Python library for finding Longest Increasing Subsequence (LIS) in an integer array

Ongoing research training transformer models at scale

Dataset, streaming, and file system extensions maintained by TensorFlow SIG-IO

Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

Fast parallel CTC.

This is now the official location of the Merlin project.

unofficial LAME MP3 Encoder

Reference implementation of real-time autoregressive wavenet inference

A general-purpose encoder-decoder framework for Tensorflow

A library for generalized sequence to sequence models

Text-to-Speech tutorial at SLTU 2016

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

WeChat 4.0 database decryptor - extract keys from memory, decrypt SQLCipher 4 databases, real-time message monitor

LLM inference in C/C++

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

Compare two version of an arXiv preprint with a single command.

From Early Internet Design Patterns to AI Agent Implementation — A Deep Dive into Claude Code for Developers

A high-throughput and memory-efficient inference and serving engine for LLMs

Your faithful, impartial partner for audio evaluation — know yourself, know your rivals. 真实评测，知己知彼。

A framework for efficient model inference with omni-modality models

onnx export

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

✍ WeChat Markdown Editor | 一款高度简洁的微信 Markdown 编辑器：支持 Markdown 语法、自定义主题样式、内容管理、多图床、AI 助手等特性

Text-to-text alignment algorithm for speech recognition error analysis.

Open-Source Frontier Voice AI

No description.

A Python library for editing subtitle files

No description.

这是一个基于 Cloudflare Workers 和 Pages平台的脚本,通过EDtunnel修改，使用该脚本可以自动生成VLESS、Trojan免费节点,并配置信息使用在线配置转换到 Clash、 Singbox 、Quantumult X等工具中。

Enjoy the magic of Diffusion models!

Fast and memory-efficient exact attention

Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

文颜 MCP Server 可以让 AI 自动将 Markdown 文章排版后发布至微信公众号。

MagicTryOn is a video virtual try-on framework based on a large-scale video diffusion Transformer.

PC微信Hook模块、Hook WeChat / 微信逆向、微信机器人、WeChatRobot

No description.

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Wan: Open and Advanced Large-Scale Video Generative Models

Opus codec support for Python.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

AED

Faster Whisper transcription with CTranslate2

FSA/FST algorithms, differentiable, with PyTorch compatibility.

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

Command line utility for forced alignment using Kaldi

Pybind11 bindings for Kaldi

Permanent Apple Intelligence + Xcode Predictive Code Completion for Chinese-market Mac computers

NeMo text processing for ASR and TTS

No description.

Text to speech alignment using CTC forced alignment

FAIR Sequence Modeling Toolkit 2

Python wrappers for Kaldi Levenshtein's distance and alignment code.

This is now the official location of the Kaldi project.

demos page

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Graph Neural Networks with Keras and Tensorflow 2.

Making text a first-class citizen in TensorFlow.

Fork of pbzx (www.tonymacx86.com/general-help/135458-pbzx-stream-parser.html)

example for build automake/autoconf project in bazel project

An Efficient Lexical Analyzer for Chinese

My implementations of reinforcement learning algorithms

dist-git python extra branches

No description.

Google AI Research

Linear Algebra for Java

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

Fast Parallel Tasking Programming Library using Modern C++

A simple example for test valgrind tensorflow

Main gperftools repository

TensorFlow Example Projects

A high-quality speech analysis, manipulation and synthesis system

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy

An End-to-End Architecture for Keyword Spotting and Voice Activity Detection

papers of End-To-End TTS

TensorFlow Exercises - focusing on the comparison with NumPy.

LevelDB is a fast key-value storage library written at Google that provides an ordered mapping from string keys to string values.

Phonetisaurus G2P

Models built with TensorFlow

Python code for Reinforcement Learning: An Introduction

MLDB is the Machine Learning Database

No description.

blog

record some code