Skip to content
View duj12's full-sized avatar
35 followers · 27 following
  • Xmov.ai
  • Hangzhou

Achievements

Achievement: QuickdrawAchievement: StarstruckAchievement: Pair ExtraordinaireAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: StarstruckAchievement: Pair ExtraordinaireAchievement: Pull Shark

Block or report duj12

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
duj12/README.md

👋 Hi, I'm @duj12, a graduate from Tsinghua University's Department of Engineering Physics.

👀 My research interests lie in Speech and Spoken Language Processing, Understanding, and Generation.

🌱 My primary focus areas include Automatic Speech Recognition (ASR), Voice Activity Detection (VAD), Keyword Spotting (KWS), and Language Modeling.

⏳ Currently, I'm actively working on Text-to-Speech (TTS), Zero-Shot Speech Synthesis, and Voice Cloning technologies.

💞️ I look forward to collaborating and exchanging ideas in fields such as deep learning, generative artificial intelligence, and large language models (LLMs).

📫 How to reach me: thuduj12@163.com.

Pinned Loading

  1. duj12 duj12 Public

    Config files for my GitHub profile.

  2. ASR-2Pass ASR-2Pass Public

    ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).

    HTML 94 13

  3. kws_demo kws_demo Public

    KWS demo based on CTC prefix beam search.

    Python 17 2

  4. CosyVoice CosyVoice Public

    Forked from FunAudioLLM/CosyVoice

    LLM based TTS model, providing inference/training/deployment full-stack ability.

    Python 2 1

  5. Fun-ASR-deploy Fun-ASR-deploy Public

    Forked from fengin/Fun-ASR-Nano-2512-Deploy

    使用Paraformer-streaming模型做一遍流式解码，Fun-ASR-Nano做二遍解码并使用VLLM加速，兼顾延迟和准确率。

    Python 1

  6. Fun-ASR-vllm Fun-ASR-vllm Public

    Forked from yuekaizhang/Fun-ASR-vllm

    Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.

    Python