GitYCC
I'm an ML engineer/researcher, familiar with CV, NLU, and Rec. I also have experience in high-QPS ML systems. Meanwhile, I'm a blogger and guitar singer.
Taipei, Taiwan
Pinned Repositories
context-engineering-intro-zh
Context engineering 是新的 Vibe Coding —— 它是讓 AI 程式助理真正發揮作用的關鍵方式。Claude Code 是目前最適合做這件事的工具，所以這個 repo 會以它為核心，但其實你也可以把這個策略應用在任何 AI 程式助理上！
crnn-pytorch
Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition using Pytorch
g2pW
Chinese Mandarin Grapheme-to-Phoneme Converter. 中文轉注音或拼音 (INTERSPEECH 2022)
machine-learning-papers-summary
機器學習論文筆記
NTU_HYLee_MachineLearning_Homework
作業分享：台大李宏毅 (Hung-Yi Lee) 教授的Machine Learning (2016, Fall)
TempDD
Template-Driven Development Framework for AI-Augmented Coding
clairaudience
Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning (ASRU2023)
generative-fusion-decoding
Generative Fusion Decoding (GFD) is a novel framework for integrating Large Language Models (LLMs) into multi-modal text recognition systems like ASR and OCR, improving performance and efficiency by enabling seamless fusion without requiring re-training.
MR-Models
聯發創新基地（MediaTek Research) 致力於研究基礎模型。我們將研究體現在適合繁體中文使用者的模型上，並在使用權許可的情況下，提供模型給學術界研究或產業界使用。
TASTE-SpokenLM
A method that directly addresses the modality gap by aligning speech token with the corresponding text transcription during the tokenization stage.
GitYCC's Repositories
GitYCC/g2pW
Chinese Mandarin Grapheme-to-Phoneme Converter. 中文轉注音或拼音 (INTERSPEECH 2022)
GitYCC/crnn-pytorch
Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition using Pytorch
GitYCC/NTU_HYLee_MachineLearning_Homework
作業分享：台大李宏毅 (Hung-Yi Lee) 教授的Machine Learning (2016, Fall)
GitYCC/context-engineering-intro-zh
Context engineering 是新的 Vibe Coding —— 它是讓 AI 程式助理真正發揮作用的關鍵方式。Claude Code 是目前最適合做這件事的工具，所以這個 repo 會以它為核心，但其實你也可以把這個策略應用在任何 AI 程式助理上！
GitYCC/machine-learning-papers-summary
機器學習論文筆記
GitYCC/TempDD
Template-Driven Development Framework for AI-Augmented Coding
GitYCC/Tensorflow_Tutorial
Step by step, Let you learn how to use tensorflow in practical.
GitYCC/spec-kit
💫 規格驅動開發入門工具套件
GitYCC/Open-Vibe-Developers
Let’s contribute to bringing vibe-coding into the realm of production-grade engineering 🚀
GitYCC/traditional-chinese-text-recogn-dataset
繁體中文OCR文字識別數據集
GitYCC/phonetic_mlm
Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition
GitYCC/gomoku-vibe-example
GitYCC/git-tutorial
GitYCC/pigment-mixing-py
GitYCC/YCNote
GitYCC/BMAD-METHOD-zh
Breakthrough Method for Agile Ai Driven Development
GitYCC/CenterNet
Object detection, 3D detection, and pose estimation using center point detection:
GitYCC/CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
GitYCC/d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被全球175所大学采用教学。
GitYCC/deep-text-recognition-benchmark
Text recognition (optical character recognition) with deep learning methods.
GitYCC/digital_speech_processing_LSLee
GitYCC/drawnix
开源白板工具（SaaS），一体化白板，包含思维导图、流程图、自由画等。All in one open-source whiteboard tool with mind, flowchart, freehand and etc.
GitYCC/FastChat-Yen
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
GitYCC/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
GitYCC/g2pM
A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset
GitYCC/LLaMA-Efficient-Tuning
Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan)
GitYCC/pycontw-blog
Blog for PyCon Taiwan
GitYCC/pycontw-post-calendar-tool
GitYCC/pypinyin-g2pW
基于 g2pW 提升 pypinyin 的准确性
GitYCC/S3Tokenizer
Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice