Deep Learning Image Segmentation: Theory and Practice

We Speech Transcript based on LLM, in 300 lines of code.

A SOTA lightweight multilingual LLM

llama3 implementation one matrix multiplication at a time

Offline Quantization Tools for Deploy.

User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)

Goodness of Pronunciation using Kaldi on Epa-DB database

Kaldi-based goodness of pronunciation (GOP)

Forced alignment and Goodness of Pronunciation (GOP) with DNN support. Bases on Kaldi.

Wake-up-word(WUW)system is an emerging development in recent times. Voice interaction with systems have made life ease and aids in multi-tasking. Apple, Google, Microsoft, Amazon have developed a c…

EfficientNet-Absolute Zero for Continuous Speech Keyword Spotting

machine learning algorithms and implementations

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

Towards hot directions in industrial end to end speech recognition

数据挖掘、计算机视觉、自然语言处理、推荐系统竞赛知识、代码、思路

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

magicspeech competition recipe

A No-Recurrence Sequence-to-Sequence Model for Speech Recognition

A resource for learning about Machine learning & Deep Learning

📃 以夯实基础为主要目的，慢慢持续更新，具体GitBook可见：

A PyTorch-based Speech Toolkit

**Official** 李宏毅 (Hung-yi Lee) 機器學習 Machine Learning 2021 Spring

Deep Learning on Human Language Processing (2020, Spring) NTU-EECS

Joint CTC-Attention End-to-end Speech Recognition - PyTorch Implementation (Deep Learning for Human Language Processing Special Project)

notes about machine learning

End-to-End Speech Processing Toolkit