Seacrowd eval base-code for ThaiLLM-Leaderboard

South-East Asia Large Language Models

MixSP: Space Decomposition for Sentence Embedding (ACL)

WangchanX Eval

WangchanX Fine-tuning Pipeline

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Embedding Representation for Indonesian Sentences!

8-week curriculum for AI Builders

Thai Natural Language Processing in Python.

WangChanGLM 🐘 - The Multilingual Instruction-Following Model

Implementation of ConGen: Unsupervised Control and Generalization Distillation For Sentence Representation (Finding of EMNLP 2022).

KhanomTan TTS (ขนมตาล) is an open-source Thai text-to-speech model that supports multilingual speakers such as Thai, English, and others.

Python Thai Automatic Speech Recognition

The implementation of CL-ReLKT (NAACL-2022)

Pytorch implementation of paper: Thai Nested Named Entity Recognition

Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

Bootstrapped Unsupervised Sentence Representation Learning (ACL 2021)

State-of-the-Art Text Embeddings

Acceptance rates for the major AI conferences

Benchmark for Thai sentence representation

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

Finetune wav2vec2-large-xlsr-53 with Thai Common Voice Corpus 7.0

A Japanese tokenizer based on recurrent neural networks

Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation (ACL 2021 Findings).

Thai_TTS is the project about training "Text to Speech in Thai" using Tacotron2 by NVIDIA.

A library for transfer learning by reusing parts of TensorFlow models.