<!-- GitHub Profile README - Stardust --> <!-- Dynamic Typing Header --> --- > 星尘纵易散,银汉自长盈。清辉苍穹倾,同歌寥廓永夜明。 --- About Me > Sophomore student passionate about Cloud Native infrastructure and High Performance Computing.…
<!-- GitHub Profile README - Stardust -->
<!-- Dynamic Typing Header -->
---
> 星尘纵易散,银汉自长盈。清辉苍穹倾,同歌寥廓永夜明。
---
About Me
> Sophomore student passionate about Cloud Native infrastructure and High Performance Computing. Currently working at 39 AI / FishAudio as an Infrastructure Engineer, specializing in GPU cluster operations at scale.
>
> Previously an Audio Algorithm Engineer focusing on TTS/SVC model development. Transitioned to Infrastructure to build the systems that power AI — from bare-metal GPU clusters to Kubernetes-orchestrated training pipelines.
Stardust
═══════════════════════
Sophomore
Infra Engineer
FishAudio
Cloud Native
HPC & GPU Cluster
Ex-Audio Algorithm
═══════════════════════---
Tech Stack
<!-- Infrastructure -->
<!-- Programming -->
<!-- MLOps -->
---
Featured Projects
> Projects from the FishAudio team that I contribute to
<!-- FishAudio Organization Stats -->
| Project | Description | Stars |
|---------|-------------|-------|
| fish-speech | SOTA Open Source TTS | !Stars |
| so-vits-svc | SoftVC VITS Singing Voice Conversion | !Stars |
| Bert-VITS2 | VITS2 backbone with multilingual-bert | !Stars |
| ZeroBot-Plugin | OneBot plugin based on ZeroBot | !Stars |
| fish-diffusion | An easy to understand TTS / SVS / SVC framework | !Stars |
---
What I Do
<!-- Scale at a glance -->
> Operating 100–1,000+ GPU training clusters, petabyte-scale storage, and 100Gbps+ public network (our own ASN AS402567) for FishAudio. Dual-stack scheduling with Slurm (HPC/bare-metal training) and Kubernetes (services & MLOps), backed by Ceph and friends — the substrate beneath our production TTS models.
mermaid
mindmap
root((Stardust))
Infrastructure
GPU Cluster Operations
Kubernetes Management
CI/CD Pipelines
MLOps
Data Pipeline Optimization
Model Training Workflows
Distributed Computing
Collaboration
Algorithm Team Support
Open Source Contribution
Learning
Distributed Systems
Cloud Native Tech
AI Infrastructure---
GitHub Stats
---
Contact
---
<!-- Visitor Counter -->
> *"In the world of Infra, every star matters."*
Building the infrastructure for the AI era
-
vits ⑂
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Python ★ 164 2y agoExplain → -
emotional-vits-genshin ⑂
无需情感标注的情感可控原神+崩三全人物语音合成模型，基于VITS
Jupyter Notebook ★ 22 3y agoExplain → -
openclaw-workspace
OpenClaw AI 助手专用工作空间 - 存储 AI 技能、项目代码和自动化脚本
Python ★ 7 1mo agoExplain → -
overwatch-dglab
打守望先锋被打了真的会电你 | Get zapped when you take damage in Overwatch
Python ★ 3 15d agoExplain → -
Stardust-minus
No description.
★ 2 12h agoExplain → -
AutoApiP ⑂
E5 自动续期
Python ★ 2 3y agoExplain → -
AIvoice-Web ⑂
No description.
JavaScript ★ 2 2y agoExplain → -
MQTTS ⑂
mandarin version of MQTTS
Python ★ 2 2y agoExplain → -
mirai ⑂
高效率 QQ 机器人支持库
Kotlin ★ 2 3y agoExplain → -
Dice ⑂
QQ Dice Robot For TRPG QQ跑团掷骰机器人
C++ ★ 1 1y agoExplain → -
StyleTTS2 ⑂
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
Python ★ 1 1y agoExplain → -
CrepeSR ⑂
SR
★ 1 3y agoExplain → -
contentvec-wenet ⑂
speech self-supervised representations，based on wenet speech dataset
★ 1 3y agoExplain → -
Comprehensive-Transformer-TTS ⑂
A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS
★ 1 3y agoExplain → -
cloudfront_nodecat ⑂
A python script to catch aws cloudfront ghost nodes in china.
★ 1 5y agoExplain → -
Arknights-Draw ⑂
有关明日方舟的模拟抽卡api
★ 1 4y agoExplain → -
AImage ⑂
> 基于stable-diffusion-webui的AI绘画脚本
Lua ★ 1 3y agoExplain → -
-ChatGPT_VITS ⑂
一个使用OpenAI接口链接VITS模型的语音对话系统GUI
★ 1 3y agoExplain → -
MagVITS ⑂
VITS with phoneme-level prosody modeling based on MaskGIT
Python ★ 1 1y agoExplain → -
stable-diffusion-forDice ⑂
Stable Diffusion，对API进行了修改使之可用于Dice
Python ★ 1 3y agoExplain → -
vllm ⑂
A high-throughput and memory-efficient inference and serving engine for LLMs
★ 0 2h agoExplain → -
NextChat ⑂
✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
TypeScript ★ 0 8mo agoExplain → -
fish-speech ⑂
SOTA Open Source TTS
Python ★ 0 1y agoExplain → -
dify ⑂
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
★ 0 1y agoExplain → -
openai-gemini ⑂
Gemini ➜ OpenAI API proxy. Serverless!
JavaScript ★ 0 2y agoExplain → -
ssJSKFJDJ ⑂
No description.
★ 0 3y agoExplain → -
SurfingTutorial ⑂
给中国新大学生的网上冲浪和计算机使用教程
★ 0 3y agoExplain → -
vits2_pytorch ⑂
unofficial vits2-TTS implementation in pytorch
Python ★ 0 2y agoExplain → -
DPHuBERT ⑂
INTERSPEECH 2023: "DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models"
Python ★ 0 2y agoExplain → -
glow-svc ⑂
singing voice conversion based on glow-tts
Python ★ 0 2y agoExplain → -
go-cqhttp ⑂
cqhttp的golang实现，轻量、原生跨平台.
★ 0 2y agoExplain → -
docker-ubuntu-ttyd ⑂
No description.
Dockerfile ★ 0 2y agoExplain → -
RVC-MultiSpeaker-WebUI ⑂
liujing04/Retrieval-based-Voice-Conversion-WebUI reconstruction project
Python ★ 0 3y agoExplain → -
RVC-MultiSpeaker ⑂
Voice data <= 10 mins can also be used to train a good VC model!
★ 0 3y agoExplain → -
NaturalSpeech2 ⑂
No description.
Python ★ 0 3y agoExplain → -
vits_chinese ⑂
Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support streaming out!
Python ★ 0 3y agoExplain → -
MoeGoe ⑂
MoeGoe Azure Cloud Function API
Python ★ 0 3y agoExplain → -
MB-iSTFT-VITS ⑂
Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform
★ 0 3y agoExplain → -
HierTTS ⑂
No description.
★ 0 3y agoExplain → -
pits ⑂
PITS: Variational Pitch Inference for End-to-end Pitch-controllable TTS without External Pitch Predictor
Python ★ 0 3y agoExplain → -
fish-diffusion ⑂
An easy to understand TTS / SVS / SVC framework
Python ★ 0 3y agoExplain → -
someinteresting ⑂
Doprax一键五协议共存脚本：Xray内核，支持vless，vmess，trojan，shadowsocks，socks五协议同时在线，支持自定义伪装网站，CDN自选IP可提速
★ 0 3y agoExplain → -
diff-svc ⑂
An Implementation of Singing Voice Conversion Based on Diffsinger
★ 0 3y agoExplain → -
onebot-kotlin ⑂
OneBot标准的Kotlin实现及mirai插件 - 原cqhttp-mirai
Kotlin ★ 0 3y agoExplain → -
OlivOS-VITS-ChatGPT ⑂
OlivOS Plugin Template For Python
★ 0 3y agoExplain → -
MB-iSTFT-VITS-with-AutoVocoder ⑂
Incorporating AutoVocoder to MB-iSTFT-VITS
★ 0 3y agoExplain → -
pytjen ⑂
pytjen!
Python ★ 0 3y agoExplain → -
Honkai-Appdata-Decryptor ⑂
A tool to decrypt .unity3d file located in Appdata/LocalLow/miHoYo/Honkai Impact 3/Data/data/...
C++ ★ 0 3y agoExplain → -
vcpkg ⑂
C++ Library Manager for Windows, Linux, and MacOS
CMake ★ 0 3y agoExplain → -
Grasscutter ⑂
A server software reimplementation for a certain anime game.
Java ★ 0 3y agoExplain → -
ZeroBot-Plugin ⑂
基于 ZeroBot 的 OneBot 插件
Go ★ 0 3y agoExplain → -
MagiskOnWSA ⑂
Integrate Magisk root and OpenGApps into WSA (Windows Subsystem for Android)
★ 0 4y agoExplain → -
Small_House_of_Xi ⑂
晞の小屋 Electron
JavaScript ★ 0 3y agoExplain → -
VFIN ⑂
No description.
★ 0 5y agoExplain → -
GenshinHelper ⑂
GenshinHelper 随便写写
Kotlin ★ 0 4y agoExplain → -
mirai-device-generator ⑂
No description.
Kotlin ★ 0 4y agoExplain → -
something ⑂
No description.
★ 0 4y agoExplain → -
Mirai-iOS ⑂
在iOS和iPadOS上运行Mirai（实验性）
★ 0 4y agoExplain → -
EnableQQLog ⑂
启用qq的log
★ 0 5y agoExplain → -
Stardust-gitbook
星尘的文档
★ 0 3y agoExplain → -
video2x ⑂
A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley 2, 2018.
★ 0 4y agoExplain → -
Ghost-Downloader-2 ⑂
一个基于PyQt5制作GUI的劲爆多线程下载器
Python ★ 0 4y agoExplain → -
TwoThornApes ⑂
MCSManager 9 Summer 主题
★ 0 4y agoExplain → -
v2ray-heroku ⑂
用于在 Heroku 上部署 V2Ray WebSocket。
★ 0 5y agoExplain →
No repos match these filters.