qiguanjie

fuzi.mingcha

夫子•明察司法大模型是由山东大学、浪潮云、**政法大学联合研发，以 ChatGLM 为大模型底座，基于海量中文无监督司法语料与有监督司法微调数据训练的中文司法大模型。该模型支持法条检索、案例分析、三段论推理判决以及司法对话等功能，旨在为用户提供全方位、高精准的法律咨询与解答服务。

DISC-LawLLM

DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services

LexiLaw

LexiLaw - 中文法律大模型

autocut

用文本编辑器剪视频

alpaca-lora

Instruct-tune LLaMA on consumer hardware

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

ICD

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"

ICD

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"

langchain

🦜🔗 Build context-aware reasoning applications

SRILM

Mirror of SRILM

MCWS

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

llama

Inference code for Llama models

Megatron-LLaMA

Best practice for training LLaMA models in Megatron-LM

OpenTransformer

A No-Recurrence Sequence-to-Sequence Model for Speech Recognition

WeTextProcessing

Text Normalization & Inverse Text Normalization

PunctuationModel

中文标点符号模型，可以给文本添加标点符号。

PPASR

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

Cross-Domain-Chinese-Punctuation-Prediction

CDCPP: Cross-Domain Chinese Punctuation Prediction

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

gensim-data

Data repository for pretrained NLP models and NLP corpora.

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

FunClip

Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.

vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

uroman

Universal Romanizer that can convert any unicode script to roman (latin) script

vqwordseg

Unsupervised phone and word segmentation using dynamic programming on self-supervised VQ features.

DSegKNN

kaldi

kaldi-asr/kaldi is the official location of the Kaldi project.

pytorch-softdtw-cuda

Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.