Pinned Repositories
2017-JDD-Global-Data-Explorer-Competition
2017京东金融全球数据探索者大赛(3th place)
AI
projects for CS170 Intro to AI
BHumanCodeRelease
The official B-Human code releases
Chinese_Polyphone_Disambiguation
论文复现，使用pos标记进行中文多音字消歧
CS_141
Full-parallel_100x_real_time_End2EndTTS
Full parallel, 100x_real_time, End2EndTTS ,TTS,real time,TTS ,Chinese ,Mandarin, English
Neural-Stock-Market-Prediction
Uses back-propagating artificial neural networks (ANNs) and historic stock market prices to predict the future trend of stock exchange.
pigeon
A spatial extension to Pig Latin
SimpleRecurrentUnits-SRU-
SRU based acoustic model for SPSS
VMTTS
suzhiba's Repositories
suzhiba/Full-parallel_100x_real_time_End2EndTTS
Full parallel, 100x_real_time, End2EndTTS ,TTS,real time,TTS ,Chinese ,Mandarin, English
suzhiba/VMTTS
suzhiba/alpaca-lora
Instruct-tune LLaMA on consumer hardware
suzhiba/audiocaps
🔊 Repository for our NAACL-HLT 2019 paper: AudioCaps
suzhiba/AudioLDM
AudioLDM: Generate speech, sound effects, music and beyond, with text.
suzhiba/AudioLDM-training-finetuning
AudioLDM training, evaluation, and finetuning.
suzhiba/AudioLDM2
Text-to-Audio/Music Generation
suzhiba/ChatGPT
Lightweight package for interacting with ChatGPT's API by OpenAI. Uses reverse engineered official API.
suzhiba/chatgpt_academic
科研工作专用ChatGPT拓展，特别优化学术Paper润色体验，支持自定义快捷按钮，支持自定义函数插件，支持markdown表格显示，Tex公式双显示，代码显示功能完善，新增本地Python/C++/Go项目树剖析功能/项目源代码自译解能力，新增PDF和Word文献批量总结功能/PDF论文全文翻译功能
suzhiba/CLAP
Contrastive Language-Audio Pretraining
suzhiba/CogView
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".
suzhiba/Comprehensive-Transformer-TTS
A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS
suzhiba/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
suzhiba/DL-Art-School
TorToiSe fine-tuning with DLAS
suzhiba/ERISHA
ERISHA is a mulitilingual multispeaker expressive speech synthesis framework. It can transfer the expressivity to the speaker's voice for which no expressive speech corpus is available.
suzhiba/HanLP
中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
suzhiba/hifiTTS
中文普通话高保真语音合成 hifi TTS
suzhiba/live2d-widget
把萌萌哒的看板娘抱回家 (ノ≧∇≦)ノ | Live2D widget for web platform
suzhiba/live2d_demo
Live2D 看板娘插件 (https://www.fghrsh.net/post/123.html) 的前端 HTML 源码
suzhiba/NATSpeech
A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)
suzhiba/PhaseGAN
suzhiba/PhaseGAN-A_Phase_Informed_GAN_Vocoder
suzhiba/ppg-vc
PPG-Based Voice Conversion
suzhiba/Prosody_transfer_for_IPA_based_bilingual_TTS_system
suzhiba/PSST
Prosodic Speech Segmentation with Transformers
suzhiba/rfwave
suzhiba/speechgpt
SpeechGPT is a web application that enables you to converse with ChatGPT.
suzhiba/tango
Codes and Model of the paper "Text-to-Audio Generation using Instruction Tuned LLM and Latent Diffusion Model"
suzhiba/vall-e
An unofficial PyTorch implementation of the audio LM VALL-E
suzhiba/wechat-chatgpt
Use ChatGPT On Wechat via wechaty