uloveqian2021 Goto Github PK

asr_distill_paper

athena

An open-source implementation of sequence-to-sequence based speech processing engine

awesome-domain-llm

收集和梳理垂直领域的开源模型、数据集及评测基准。

awesome-pretrained-chinese-nlp-models

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型集合

blog_source

the source directory of my blog

clap

Contrastive Language-Audio Pretraining

colossalai-chatgpt

Making big AI models cheaper, easier, and scalable

cotext

cpt

CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

csbert-using-siamese-network

ctc-kws

Production First and Production Ready End-to-End Keyword Spotting Toolkit

ctc_convolutions

docee

🕹️ A toolkit for document-level event extraction, containing some SOTA model implementations.

emformer

asr based on emformer

featureextractionkws

SP: Feature Extraction for Speech Recognition using OFA

gaiic_task2

电商领域命名实体识别

joint-nlu

意图识别&槽位填充&bert 蒸馏

jointentityrelationextraction

Tensorflow 版三元组抽取，含线上推理代码

kan-tts

keyword-spotting-ctc

端到端语音唤醒工具箱，从模型训练到模型推理。

knncontrastiveforood

kws_train

landmark-attention

Landmark Attention: Random-Access Infinite Context Length for Transformers

lann

This is a little Annotator tool using browser；这是一个基于浏览器运行的中文三元组（命名实体识别和关系分类）联合标注工具

latte

The official implementation of Latte: Latent Diffusion Transformer for Video Generation.

mb-istft-vits

medical_nlp

Medical NLP Competition, dataset, large models, paper 医疗NLP领域 比赛，数据集，大模型，论文，工具包

mnbvc

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

model2onnx

model2onnx，将roberta和macbert模型转为onnx格式，并进行推理。

moss

An open-source tool-augmented conversational language model from Fudan University