Stars
funshine / backtrader-streamlit
Forked from yygina/backtrader基于币安（Binance）API的数字货币回测与可视化分析平台，支持现货/永续合约USDT交易对的多时间框架技术分析，通过Backtrader实现策略回测，并基于Streamlit提供交互式可视化界面。
Translate the video from one language to another and embed dubbing & subtitles.
A Conversational Speech Generation Model
fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
Uses ONNX Runtime for character role speaker identification.
tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
🤖💬 Transformer TTS: Implementation of a non-autoregressive Transformer based neural network for text to speech.
A book about Text-to-Speech (TTS) in Chinese.
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics rec…
An Open-Sourced LLM-empowered Foundation TTS System
Portable filebrowser with mobile ui ( html5 + go )
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A high-throughput and memory-efficient inference and serving engine for LLMs
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
oneAPI Deep Neural Network Library (oneDNN)
Git with a cup of tea! Painless self-hosted all-in-one software development service, including Git hosting, code review, team collaboration, package registry and CI/CD
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"
🚀 The best real-time interactive AI avatar(digital human) with on-premise deployment and <1.5 s latency.
A metasearch library that aggregates results from diverse web search services