Boomprogrammar

grok-1

Grok open release

HackerDictionary

整理一些黑客蛮力攻击常用的字典

sd-webui-regional-prompter

set prompt to divided region

ControlNet-v1-1-nightly

Nightly release of ControlNet 1.1

OpenVINO_sample

lora

Using Low-rank adaptation to quickly fine-tune diffusion models.

Style2Paints_V3

Reimplementation of Style2Paints V3

ControlLoRA

ControlLoRA: A Lightweight Neural Network To Control Stable Diffusion Spatial Information

pytorch-CycleGAN-and-pix2pix

Image-to-Image Translation in PyTorch

CAT

A CRF-based ASR Toolkit

style2paints

sketch + style = paints :art: (TOG2018/SIGGRAPH2018ASIA)

Pixeldraw

A pixel drawing application 一个像素绘画软件

CIF-PyTorch

[ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-Fire mechanism).

CIF-HieraDist

[INTERSPEECH 2023] Knowledge Transfer from Pre-trained Language Models to Cif-based Recognizers via Hierarchical Distillation

DFSMN

Tensorflow version of DFSMN

DPHuBERT

INTERSPEECH 2023: "DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models"

XPhoneBERT

XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)

FitHuBERT

FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning (INTERSPEECH 2022)

SGEM

Official PyTorch implementation of SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization (INTERSPEECH 2023 Oral Presentation)

ContextNet

PyTorch implementation of "ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context" (INTERSPEECH 2020)

UnsupSeg

Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation (INTERSPEECH 2020)

chinese-chatbot-corpus

中文公开聊天语料库

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

Emotion-Recognition-Papers

A list of papers for emotion recognition using machine learning/deep learning.

CLONE_DK

使用聊天记录和播客文章，基于chatGLM-6B训练自己的数字克隆的方案实现，包括用到的脚本和最后部署成前端页面的代码

awesome-aigc

A list of awesome AIGC works

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.

wav2vec

a simplified version of wav2vec(1.0, vq, 2.0) in fairseq

chinese_speech_pretrain

chinese speech pretrained models

SpeechT5

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing