thai2fit
Thai Model Framework
A Thai language model and text analysis framework with pre-trained word embeddings and classification benchmarks.
ULMFit Language Modeling, Text Feature Extraction and Text Classification in Thai Language. Created as part of pyThaiNLP
191 stars
14 watching
50 forks
Language: Jupyter Notebook
last commit: almost 4 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 kobkrit/tf-nlp-thai-word-embedding | An implementation of a word embedding technique using TensorFlow for Thai language processing | 11 |
 tchayintr/thbert | A pre-trained BERT model designed to facilitate NLP research and development with limited Thai language resources | 6 |
 pythainlp/pythainlp | A Python package for text processing and linguistic analysis focused on the Thai language. | 987 |
 krakenai/synthai | A deep learning-based project for segmenting Thai text into words and annotating parts of speech with high accuracy. | 41 |
 pucktada/cutkum | A tool for segmenting Thai text into words using Recurrent Neural Networks in TensorFlow. | 154 |
| pythainlp/lexicon-thai | A Thai language corpus and lexicon repository for natural language processing | 141 |
 stanford-crfm/levanter | A framework for building and training large language models with focus on reproducibility, scalability, and performance. | 516 |
 koromodako/mkctf | A CTF framework to create, build, deploy and monitor challenges | 107 |
 thaiinhk/vocabreactnative | An educational mobile app built with React Native for learning Thai vocabulary. | 37 |
 mustafaturan/omnicat | A framework providing a generalized strategy holder for text classification | 11 |
 jy0205/lavit | A unified framework for training large language models to understand and generate visual content | 528 |
 zju-m3/tablegpt-techreport | A framework that enables large language models to understand and operate on tables using natural language input and external function commands | 102 |
 rkcosmos/deepcut | A Thai word tokenization library using Deep Neural Network | 420 |
 dinghanshen/swem | A software project that implements word embedding-based models for text classification tasks and provides pre-trained embeddings and evaluation scripts. | 284 |
 sicara/tf-explain | A library providing interpretability methods for TensorFlow 2.x models | 1,018 |