Skip to content

@vistec-AI VISTEC-depa AI Research Institute of Thailand

Change the repository type filter

All

    Repositories list

    36 repositories

    • WangchanX

      Public
      WangchanX Fine-tuning Pipeline
      Jupyter Notebook
      •
      Apache License 2.0
      •6•42•1•0•Updated Oct 4, 2024Oct 4, 2024

    • crfcut

      Public
      Thai sentence segmentation with conditional random fields
      scb-mt-en-th-2020
      Jupyter Notebook
      •3•15•0•3•Updated Jun 17, 2024Jun 17, 2024

    • Bilingual-Financial-NER-Model

      Public
      Python
      •0•3•0•0•Updated Jun 11, 2024Jun 11, 2024

    • vistec-ai.github.io

      Public
      HTML
      •0•0•0•0•Updated May 29, 2024May 29, 2024

    • capital_market_text_data

      Public
      0•1•0•0•Updated May 29, 2024May 29, 2024

    • WangchanLion

      Public
      Python
      •0•5•0•0•Updated May 29, 2024May 29, 2024

    • WangchanX-Eval

      Public
      WangchanX Eval
      Python
      •
      Apache License 2.0
      •1•9•0•0•Updated May 29, 2024May 29, 2024

    • thai2nmt

      Public
      English-Thai Machine Translation Models
      Python
      •
      Apache License 2.0
      •6•28•2•1•Updated May 3, 2024May 3, 2024

    • Thai-NNER

      Public
      Pytorch implementation of paper: Thai Nested Named Entity Recognition
      acl2022thai-nner
      Python
      •
      MIT License
      •7•39•2•0•Updated Jan 8, 2024Jan 8, 2024

    • thai2transformers

      Public
      Pretraining transformer based Thai language models
      transformerspretrained-modelsthai
      Jupyter Notebook
      •
      Apache License 2.0
      •22•116•9•3•Updated Nov 6, 2023Nov 6, 2023

    • thai2nmt_preprocess

      Public
      Python
      •
      Apache License 2.0
      •1•3•0•2•Updated Nov 21, 2022Nov 21, 2022

    • colab

      Public
      Collections of Google Colab notebooks and some data.
      Jupyter Notebook
      •8•7•0•1•Updated Sep 30, 2022Sep 30, 2022

    • commonvoice-th

      Public
      Kaldi recipe to train commonvoice corpus in Thai language
      Shell
      •8•36•3•1•Updated Aug 12, 2022Aug 12, 2022

    • mmocr

      Public
      OpenMMLab Text Detection, Recognition and Understanding Toolbox
      Python
      •
      Apache License 2.0
      •747•0•0•0•Updated Jul 25, 2022Jul 25, 2022

    • EasyOCR

      Public
      Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
      Python
      •
      Apache License 2.0
      •3.1k•2•0•0•Updated Jul 21, 2022Jul 21, 2022

    • SynthMIDI

      Public
      A single-note classification dataset generated from MIDI file.
      Python
      •
      GNU General Public License v3.0
      •0•0•2•0•Updated Jun 27, 2022Jun 27, 2022

    • wav2vec2-large-xlsr-53-th

      Public
      Finetune wav2vec2-large-xlsr-53 with Thai Common Voice Corpus 7.0
      Jupyter Notebook
      •
      Creative Commons Attribution Share Alike 4.0 International
      •12•45•3•1•Updated Apr 23, 2022Apr 23, 2022

    • WSSET

      Public
      TF2 implementation of paper: Self-supervised Deep Metric Learning for Pointsets, ICDE 2021
      Python
      •0•7•0•0•Updated Mar 7, 2022Mar 7, 2022

    • vistec-ser

      Public
      Speech Emotion Recognition using PyTorch sponsored by AIS and VISTEC-DEPA AIResearch Institute Thailand.
      Python
      •
      Apache License 2.0
      •5•17•2•0•Updated Nov 6, 2021Nov 6, 2021

    • thwiki-text

      Public
      Python
      •0•4•0•0•Updated Sep 29, 2021Sep 29, 2021

    • pdf2parallel

      Public
      Extract en-th parallel sentences from PDFs
      scb-mt-en-th-2020
      Python
      •
      Other
      •1•2•0•0•Updated Aug 20, 2021Aug 20, 2021

    • ai-builders-orientation

      Public
      Lesson 0 - Orientation
      Jupyter Notebook
      •
      MIT License
      •7•2•0•1•Updated Jul 6, 2021Jul 6, 2021

    • dataset-releases

      Public
      15•36•1•0•Updated Mar 26, 2021Mar 26, 2021

    • generated_reviews_enth

      Public
      Generated product reviews dataset for machine translation quality estimation, part of [scb-mt-en-th-2020](https://arxiv.org/pdf/2007.03541.pdf)
      Jupyter Notebook
      •
      Other
      •0•0•0•0•Updated Dec 4, 2020Dec 4, 2020

    • ai2api

      Public
      Productionize NLP models trained on Pytorch by AIResearch.in.th
      Jupyter Notebook
      •
      Apache License 2.0
      •1•1•0•0•Updated Oct 7, 2020Oct 7, 2020

    • sme-depa

      Public
      Help small businesses make money from their transaction data; workshop at depa
      Jupyter Notebook
      •
      Other
      •4•7•0•0•Updated Aug 12, 2020Aug 12, 2020

    • nlp

      Public
      🤗nlp – Datasets and evaluation metrics for Natural Language Processing in NumPy, Pandas, PyTorch and TensorFlow
      Python
      •
      Apache License 2.0
      •2.7k•0•0•0•Updated Jul 14, 2020Jul 14, 2020

    • model-releases

      Public
      3•14•0•0•Updated Jun 22, 2020Jun 22, 2020

    • scb_workshop

      Public
      2•1•0•0•Updated Jun 3, 2020Jun 3, 2020

    • thai_websites_crawler

      Public
      Scripts for crawling the 500 most visited websites in Thailand according to Alexa for `th` and `en` parallel texts.
      scb-mt-en-th-2020
      Python
      •
      Apache License 2.0
      •2•5•0•0•Updated May 6, 2020May 6, 2020