Eric Lam's Projects
A simple way to train and use NLP models with multi-GPU, TPU, mixed-precision
Revolutionize your development workflow with AI-powered code assistance, automating mock tests, suggestions, and unit test generation in a single Python CLI tool.
An open-source NLP research library, built on PyTorch.
A crawler for related youtube channels. Why not?
A categorized collection of Android Open Source Projects, More powerful web version:
The Android application providing user with REST-based interface for utilizing built-in Android's TTS engine. The web service is highly customizable via LUA scripting language.
one script for xls-r/xlsr/whisper fine-tuning
ASR text preprocessing utility
An Open-source Streaming High-fidelity Neural Audio Codec
Unlock the Power of LLM: Explore These Datasets to Train Your Own ChatGPT!
Collection Of Automated Language Model Assessment
A list of awesome machine question answering dataset - 機器問答數據集
Code for "A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies."
Fine tuning bert for text generation
bruteforce is all you need in a unstable system
`bindtorchaudio` is a Python package that allows for easy installation of the `torchaudio` library, which provides audio processing functionalities for the PyTorch machine learning framework.
Needs to generate some texts to test if my GUI rendering codes good or not. so I made this.
Cantoboard - Smart Cantonese Keyboard on iOS
Scrape cantonese syllables from CUHK Multi-function Chinese Character Database.
CCL2019,“小牛杯”中文幽默计算任务的数据集及baseline
CGED & CSC
Input-Method Tables in CIN Format
A Chinese KBQA dataset with SPARQL annotations.
Audio Codec Speech processing Universal PERformance Benchmark
An orchestration platform for the development, production, and observation of data assets.
Unified QA with different modality input
🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools