VikingMew's repositories
ChatGLM-6B
ChatGLM-6B:开源双语对话语言模型
ChatGPT
Reverse engineered ChatGPT API. Uses official model same as the website.
DeepSpeedExamples
Example models using DeepSpeed
DiffSinger
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Forked and maintained by the OpenVPI community
dolly
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
emotional-vits
无需情感标注的情感可控语音合成模型,基于VITS
hubert
HuBERT content encoders for: A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
MidJourney-Wrapper
MidJourney wrapper in Discord.
MoeSS
使用C++ OnnxRuntime 重构了Tacotron2、VITS、SoVIts、DiffSvc和DiffSinger推理的集成UI软件
MOSS
An open-source tool-augmented conversational language model from Fudan University
open_flamingo
An open-source framework for training large multimodal models
OpenChineseLLaMA
Inference code for LLaMA models
python-inoreader
Python wrapper of Inoreader API
Retrieval-based-Voice-Conversion-WebUI
Voice data <= 10 mins can also be used to train a good VC model!
RSSHub
🍰 Everything is RSSible
RSSHub-python
A RSSHub for Pythonista
silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector, Language Classifier and Spoken Number Detector
so-vits-svc
SoftVC VITS Singing Voice Conversion
so-vits-svc-4.0-v2
SoftVC VITS Singing Voice Conversion
Sovits
An implementation of the combination of Soft-VC and VITS
stable-diffusion-webui
Stable Diffusion web UI
stablediffusion
High-Resolution Image Synthesis with Latent Diffusion Models
vits-raw
VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai
vocoders
DiffSinger community vocoders release page
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
youtube-dl
Command-line program to download videos from YouTube.com and other video sites
z-bench
Z-Bench 1.0 by 真格基金:一个麻瓜的大语言模型中文测试集。Z-Bench is a LLM prompt dataset for non-technical users, developed by an enthusiastic AI-focused team in Zhenfund.