Eric Lam

awesome-chatgpt-dataset. Unlock the Power of LLM: Explore These Datasets to Train Your Own ChatGPT!

TextRL. Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

Codec-SUPERB. Audio Codec Speech processing Universal PERformance Benchmark

tw_stocker. keep tracking and store taiwan stock information - 每天更新台股歷史資料庫

TFkit. 🤖📇 handling multiple nlp task in one pipeline

SpeechMix. Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together

asr-trainer. one script for xls-r/xlsr/whisper fine-tuning

vall-e-encodec. Python

BertGenerate. Fine tuning bert for text generation

aidev. Revolutionize your development workflow with AI-powered code assistance, automating mock tests, suggestions, and unit test generation in a single Python CLI tool.

gpu-info-api. 🐱‍💻 GPU Info API is an API that provides detailed information about Nvidia, AMD, and Intel GPUs. The information is extracted from Wikipedia and stored in JSON format.

NLPrep. 🍳 NLPrep - dataset tool for many natural language processing task

BDG. Code for "A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies."

Phraseg. Phraseg - 一言：新詞發現工具包

FTA. Technical Analysis on Cryptocurrency

wav2vec2-xlsr-multilingual-56. 56 language, 1 model Multilingual ASR

ChineseErrorDataset. CGED & CSC

asrp. ASR text preprocessing utility

nlp2go. 🏃 hosting nlp models in one line

MMLM. Toward Multi Modality Language Model - implementation of GPT-4o/Project Astra

awesome-question-answering-dataset. A list of awesome machine question answering dataset - 機器問答數據集

nlp2. ⚙️Tool for NLP - handle file and text

pretrain_bart. training BART from scratch

SnapShare. Linking Your Phone To Computer Browser With Socket.io.

whisper-live-asr-demo. run whisper on CPU/GPU server

wav2vec-u-exp. Build and Run Wav2vec Unsupervised Experiment

DevLEGO. Create your development Env like LEGO blocks, run your projects on any device - be it a PC, Web, Phone or Tablet!

react-media-viewer. Ready to go Media Player Component for React.

GemmaOmni. Python

pytorch-tta. Pytorch implementation of "Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning".

hubert-cluster-code. Extract clustering feature from hubert

GSQA. Generative Spoken Question Answering

hubert-pretrain. using huggingface trainer to pre-train hubert

audio-preprocessing-pipeline. Python

fbcrawler. Python

PPA. Prompt Pool Agent

codec-arena. HTML

fastpages. Jupyter Notebook

awesome-evaluation-lm. Collection Of Automated Language Model Assessment

survey-builder. survey builder for human evaluation

DG-Showcase. Showcase for "A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies."

bindtorchaudio. `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.

Data2QA. Unified QA with different modality input

tts-corpus-creator. collection of different source of TTS api for generating corpus.

SoundON. Python

diff-aspect-set-dg. Python

open-s1-zh. Python

dpr-multilingual. A multilingual version of DPR

leverage-lm. small lm + RAG > LLM

huggingface_notebook. Jupyter Notebook

WrapSlurm. Python

shows. lib for system monitoring with CPU/GPU/DISK/MEM/NET

uni-superb. Python

twcc-usage-slack-bot. TWCC GPU Usage Notification Slack Bot

bforce. bruteforce is all you need in a unstable system