Pinned Repositories
AstrBot
✨ 一站式 LLM 聊天机器人平台及开发框架 ✨ 支持 QQ、QQ频道、Telegram、企微、飞书、钉钉 | 知识库、MCP 服务器、OpenAI、DeepSeek、Gemini、硅基流动、月之暗面、Ollama、OneAPI、Dify
chinese-hubert-soft
f5-tts-trtllm
Framer
Official PyTorch implementation of "Framer: Interactive Frame Interpolation".
hifigan-yingram-vc
vc
inferStreamHiFiGAN
StreamHiFiGAN offers a HiFiGAN vocoder model optimized for streaming inference, providing real-time audio synthesis capabilities.
natsume
A Japanese text frontend processing toolkit
PM-EVC
This is the official implement of A Controllable Emotion Voice Conversion Framework with Pre-trained Speech Representations
RAFT-Softsplat-VFI
Video Frame Interpolation (RAFT + Softsplat)
splinter21's Repositories
splinter21/AstrBot
✨ 一站式 LLM 聊天机器人平台及开发框架 ✨ 支持 QQ、QQ频道、Telegram、企微、飞书、钉钉 | 知识库、MCP 服务器、OpenAI、DeepSeek、Gemini、硅基流动、月之暗面、Ollama、OneAPI、Dify
splinter21/ngram-punctuator
An N-gram punctuator for Chinese and English.
splinter21/opencpop_textgrid_fix
splinter21/SAC
Trainging, inference, and testing of the SAC speech codec model.
splinter21/Anime-Llasa-3B-Captions-Demo
local version for OmniAICreator/Anime-Llasa-3B-Captions-Demo
splinter21/arti-6
Official implementation of ARTI-6: Six-dimensional Articulatory Speech Encoding
splinter21/Conan
Official Implementation of "Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion"
splinter21/dllm
dLLM: Training Diffusion Large Language Models Made Simple
splinter21/drax
Drax: Speech Recognition with Discrete Flow Matching
splinter21/ExpressiveSpeech
splinter21/FireRedTTS2
Long-form streaming TTS system for multi-speaker dialogue generation
splinter21/FlashI2V
An official implementation of FlashI2V.
splinter21/freegan
This repository provides a unofficial PyTorch implementation of FreeGAN
splinter21/GOOFER
GOOFER because it's just me goofing around attempting speech Source Filter
splinter21/HarmonicNoiseSplitTrainingSet
自动生成用于气声谐波分离的数据集，无需训练ddsp
splinter21/HoloCine
splinter21/LunaTranslator
视觉小说翻译器 / Visual Novel Translator
splinter21/mmaudiosep
splinter21/music-rfm
Open Source code for our paper, Steering Autoregressive Music Generation with Recursive Feature Machines (Zhao et al., 2025). aka MusicRFM
splinter21/OpenUtauMobile
OpenUtau Mobile 是一个面向移动端的开源免费歌声合成软件
splinter21/qdftPitchShift
splinter21/realtime-video
Krea Realtime 14B. An open-source realtime AI video model.
splinter21/ROSA-Tuning
ROSA-Tuning
splinter21/SimWhisper-Codec
splinter21/Timbrespace
Speech (timbre) representations model
splinter21/UltraVoice100K
This is the official repository for the UltraVoice100K dataset, providing code and dataset samples.
splinter21/vietnamese-text-normalization-for-speech
splinter21/WhisperLive-PEFT
Whisper系列のPEFTと、PEFT済のモデルを使ったストリーミング書き起こしを実装するためのリポジトリです。
splinter21/whistle
Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers
splinter21/YOLOv11n-face-detection