modelscope / KAN-TTS

#大语言模型#AgentScope: Agent-Oriented Programming for Building LLM Applications

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Enjoy the magic of Diffusion models!

#大语言模型#Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Phi4,...

强大的少样本语音转换与语音合成Web用户界面。

#大语言模型#vits2 backbone with multilingual-bert

Open-Sora： 完全开源的高效复现类Sora视频生成方案

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

#大语言模型#本地化搭建和运行 Llama2 和其他大模型

大模型Grok-1开源

#计算机科学#The easiest way to deploy agents, MCP servers, models, RAG, pipelines and more. No MLOps. No YAML.

ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

[CVPR 2024] Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework.

#大语言模型#利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

UT-Sarulab MOS prediction system using SSL models

#大语言模型#微软生成式AI课程，12课时

[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

#大语言模型#Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.