whitefu Goto Github PK

real-time-voice-cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

redpajama-data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

reflection_summary

算法理论基础知识应知应会

repcodec

Model and code for RepCodec: A Speech Representation Codec for Speech Tokenization

resnetgpt

用Resnet101+GPT搭建一个玩王者荣耀的AI

retrieval-based-voice-conversion-webui

Voice data <= 10 mins can also be used to train a good VC model!

rich-text-to-image

Rich-Text-to-Image Generation

s2v_rc

Speech2Vec Reality Check

s3prl

Self-Supervised Speech Pre-training and Representation Learning Toolkit.

sadtalker

（CVPR 2023）SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

sadtalker-video-lip-sync

本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。

sc-cnn

SC-CNN: Effective Speaker Conditioning Method for Zero-Shot Multi-Speaker Text-to-Speech Systems

sc_vall-e

Style-Controllable Zero-Shot Text to Speech Synthesizer based on VALL-E

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

sentence-splitter

Text to sentence splitter using heuristic algorithm by Philipp Koehn and Josh Schroeder.

sentence-transformers

Sentence Embeddings with BERT & XLNet

sentencepiece_chinese_bpe

使用sentencepiece中BPE训练中文词表，并在transformers中进行使用。

shakkala

Deep learning for Arabic text Vocalization - التشكيل الالي للنصوص العربية

shanghainese-tts

shared_debugging_code

shell

Linux命令行与shell脚本编程大全案例

sifigan

Official implementation of the source-filter HiFiGAN vocoder

similarities

Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包，支持亿级数据文搜文、文搜图、图搜图，python3开发，开箱即用。

simple-speaker-embedding

A speaker embedding network in Pytorch that is very quick to set up and use for whatever purposes.

skywork

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

smart-long_sentence_tts

snac

Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate

so-vits-models

收集有关so-vits-svc、TTS、SD、LLMs的各种模型、应用以及文字、声音、图片、视频有关的model。

so-vits-svc

SoftVC VITS Singing Voice Conversion

so-vits-svc-toolkit

A toolkit and documentation version of so-vits-svc.