中文

Models

98 projects · page 1 / 1

1-98 of 98
Project
Added
Created
Stars
01
whisper
OpenAI's general-purpose speech recognition model, supporting multilingual transcription, translation, language identification, and multiple model sizes for local inference.openai
2026-08-26
2022-09-16
112.5k stars
02
VibeVoice
Microsoft's open-source family of voice AI models, including long-form speech recognition, multi-speaker TTS, and real-time streaming TTS weights.microsoft
2026-07-29
2025-08-25
57.2k stars
03
kronos
An open-source foundation model for financial candlestick sequences, with pretrained tokenizers and models on Hugging Face plus forecasting and fine-tuning pipelines.shiyu-coder
2026-07-22
2025-07-01
48.0k stars
04
voxcpmaudiodeeplearningminicpm
An open-source 2B tokenizer-free multilingual TTS model for voice design, controllable cloning, and studio-quality synthesis.openbmb
2026-06-26
2025-09-16
42.6k stars
05
ChatTTSagenttext-to-speechchat
An open-source text-to-speech model for conversational dialogue with pretrained weights, multi-speaker support and fine-grained prosody control.2noise
2026-06-26
2024-05-27
40.0k stars
06
timesfm
Google’s pretrained time-series foundation model for zero-shot multivariate forecasting with PyTorch and MLX inference code.google-research
2026-06-24
2024-04-29
35.5k stars
07
unlimited-ocr
Baidu’s long-horizon document parsing OCR model with pretrained weights and Transformers, vLLM, and SGLang inference paths.baidu
2026-07-09
2026-06-18
31.1k stars
08
unilmnlppre-trained-modelunilm
Microsoft’s collection of foundation-model research with pretrained weights and code for language, vision, speech, and multimodal tasks.microsoft
2026-06-24
2019-07-23
22.2k stars
09
Qwenchineselarge-language-modelsflash-attention
The open-weight release of the Qwen family of large language models, with base and chat checkpoints plus tuning guides.QwenLM
2026-06-24
2023-08-03
22.0k stars
10
suryadeep-learningdocument-ailayout-analysis
Surya is a compact document OCR and layout vision-language model that recognizes text, layout, reading order and tables in 90+ languages, with a CLI and Python client for local inference.datalab-to
2026-11-17
2024-01-10
21.6k stars
11
FinGPTchatgptfinancefintech
An open-source financial LLM project publishing fine-tuned model weights, datasets, and robo-advisor demos for finance tasks.AI4Finance-Foundation
2026-06-24
2023-02-11
21.6k stars
12
DeepResearchagentllmartificial-intelligence
An open-weight 30B deep-research model release for long-horizon information seeking, with ReAct inference scripts, benchmarks, and demos.Alibaba-NLP
2026-06-24
2025-01-09
20.1k stars
13
Chinese-LLaMA-Alpacallmplmalpaca
Chinese-extended LLaMA and instruction-tuned Alpaca large language models, releasing LoRA weights plus training and local quantized deployment guides.ymcui
2026-06-24
2023-03-15
18.9k stars
14
lingbot-map
An open streaming 3D reconstruction foundation model with weights and demos for fast long-sequence mapping.robbyant
2026-07-09
2026-04-15
18.6k stars
15
kittentts
Kitten-TTS is a family of compact open-source text-to-speech models, from 4 MB to 1.7B parameters, supporting multilingual speech, voice cloning, and expressive control on CPUs and consumer GPUs.kittenml
2026-07-15
2025-08-05
16.9k stars
16
ace-step-1.5text2music
An open-source music generation foundation model that turns text into full songs and supports covers, repainting and vocal-to-BGM, running locally on consumer GPUs with LoRA personalization.ace-step
2026-07-21
2025-09-04
14.8k stars
17
RWKV-LMattention-mechanismdeep-learninggpt
The RWKV family of linear-time RNN language models with weights, training code, and fast inference demos.BlinkDL
2026-06-24
2021-08-08
14.8k stars
18
yuefoundation-modelsmusic-generationhuggingface
A frontier open music-generation model that plans melody and chords symbolically before rendering full songs with vocals, enabling zero-shot covers and agent-driven score editing.multimodal-art-projection
2026-09-12
2025-01-23
13.6k stars
19
CogVideollmsoravideo-generation
An open-source text-to-video and image-to-video model family with weights, inference code, and fine-tuning examples.zai-org
2026-06-24
2022-05-29
13.2k stars
20
trellis.2
A large 4B image-to-3D generative model with pretrained checkpoints, inference and training code, and high-fidelity PBR asset generation.microsoft
2026-07-09
2025-11-26
13.1k stars
21
HRMbrain-inspired-aideep-learninglarge-language-models
The official Hierarchical Reasoning Model release with training code and checkpoints for complex reasoning tasks.sapientinc
2026-06-24
2025-07-09
12.7k stars
22
MOSSchatgptdeep-learningdialogue-systems
An open-source bilingual conversational language model from Fudan, releasing weights, dialogue data, and deployment and fine-tuning code.OpenMOSS
2026-06-24
2023-04-15
12.4k stars
23
minimax-h3
A general omni-modal generative model that creates video with stereo audio from text, images, video, and audio references.minimax-ai
2026-08-09
2026-07-30
11.9k stars
24
MiniCPM
A family of compact on-device open-source language models with weights, benchmarks and deployment recipes for local inference.OpenBMB
2026-06-24
2024-01-29
11.9k stars
25
Kimi-K2
Kimi K2 is Moonshot AI's open-source family of trillion-parameter MoE language models, released as base and instruct weights for agentic, tool-use, and coding workloads. It can be deployed with vLLM, SGLang, or other inference engines.moonshotai
2026-08-26
2025-07-03
11.1k stars
26
ltx-2generative-ailtxltx-2
The official Python inference and LoRA training package for LTX-2, an audio-video generative model. It provides distilled, production-quality, image-to-video, keyframe, dubbing and HDR pipelines with memory and speed optimizations.lightricks
2026-07-15
2026-01-03
10.2k stars
27
kevdecision-modeljevqwen3
A family of small Qwen-based decision models for yes/no, multiple-choice and rating questions, with published weights, fine-tuning code and a local serving API.jaredpalmer
2026-09-21
2026-09-17
10.1k stars
28
longcat-video
A 13.6B open-weight foundation video model for text-to-video, image-to-video, and long-form continuation.meituan-longcat
2026-07-09
2025-10-25
9.6k stars
29
kimi-k3
Kimi K3 is an open-weight 2.8T-parameter native multimodal MoE model with a one-million-token context window, built for long-horizon coding, knowledge work, and reasoning.moonshotai
2026-07-27
2026-07-27
9.1k stars
30
Dolphindocument-analysislayout-analysisocr
Dolphin is ByteDance's open vision-language model for document image parsing. Its two-stage analyze-then-parse design handles digital and photographed pages, recovering layout, reading order, tables, formulas and code from PDFs and images.bytedance
2026-08-26
2025-05-13
9.1k stars
31
Qwen-Image
A 20B open image foundation model excelling at complex text rendering and precise instruction-based editing.QwenLM
2026-06-24
2025-08-03
8.5k stars
32
weathernextweatherweather-forecast
Google DeepMind's global medium-range weather and cyclone forecasting models with weights and research runtime code.google-deepmind
2026-08-09
2023-07-14
7.7k stars
33
glm-5agentic-aicodingllm
Z.ai’s open-weight MoE LLM series for agentic and long-horizon coding tasks, served via external inference engines.zai-org
2026-06-26
2026-02-09
7.5k stars
34
LLM4Decompiledecompilereverse-engineeringlarge-language-models
A family of open LLMs dedicated to decompiling binaries into readable C code, with benchmarks, training scripts, and Hugging Face checkpoints.albertan017
2026-06-24
2024-02-28
7.3k stars
35
Chinese-LLaMA-Alpaca-2alpacallamallm
A family of open Chinese LLaMA-2 base and Alpaca-2 instruction model weights with extended vocab, long-context, and RLHF variants.ymcui
2026-06-24
2023-07-18
7.1k stars
36
sensenova-u1
SenseNova-U is a family of native multimodal models for image generation, editing, interleaved text-image output and visual understanding, released with inference examples, training code and weights.opensensenova
2026-07-18
2026-04-17
6.9k stars
37
neutts
An open-source family of on-device text-to-speech models with instant voice cloning, multilingual support, and GGUF quantizations for running natural speech locally on phones, laptops, and embedded devices.neuphonic
2026-07-22
2025-10-02
6.3k stars
38
dflash
A lightweight block-diffusion draft model for speculative decoding, shipped with checkpoints and tooling that plugs into Transformers, MLX, SGLang and vLLM to speed up LLM generation.z-lab
2026-07-15
2026-01-04
6.2k stars
39
qwen3.8
The open-weight release of the Qwen3.8 large language model family for coding, agents, and long-horizon tasks.qwenlm
2026-08-19
2025-09-11
4.5k stars
40
limixfoundation-modelslimixmachine-learning
A foundation model family for tabular data whose released weights handle classification, regression, and imputation in one pass.limix-ldm-ai
2026-08-07
2025-08-27
4.4k stars
41
MOSS-TTSaudioaudio-tokenizerllm
An open-source speech model family for long-form TTS, dialogue synthesis, voice design, and streaming speech.OpenMOSS
2026-08-17
2026-02-07
4.3k stars
42
gpatext-to-speechtransformervoice-conversion
GPA is a unified autoregressive audio model for speech recognition, text-to-speech and voice conversion, released with 0.6B checkpoints, PyTorch/ONNX inference and fine-tuning pipelines.autoark
2026-07-16
2025-12-16
3.1k stars
43
tabfm
A pretrained tabular foundation model that does zero-shot classification and regression on mixed-type tables via a scikit-learn API.google-research
2026-07-09
2026-06-16
2.8k stars
44
unimate
UniMate is a unified text-to-motion model that animates diverse skeletons without per-rig retraining. The release includes checkpoints, the UniML3D dataset, training and inference code, and tools for motion in-betweening, editing and expansion.friedrich-m
2026-10-01
2026-07-22
2.7k stars
45
mai-uigui-agentgui-groundinggui-navigation
Qwen-UI-Agent (MAI-UI) is a foundation GUI agent model family for mobile, desktop, browser, and deep-search tasks. The repository releases model weights, benchmarks, and research results for real-world GUI automation.tongyi-mai
2026-08-21
2025-12-15
2.4k stars
46
MMAudioaudioaudio-synthesiscomputer-vision
MMAudio is a CVPR 2025 model for high-quality video-to-audio synthesis, generating synchronized sound from video and text with released checkpoints and code.hkchengrex
2026-08-26
2024-12-07
2.3k stars
47
MOSS-Transcribe-Diarizeaudiomultilingualspeaker-diarization
An open 0.9B end-to-end audio model for long-form transcription in 50+ languages, with speaker diarization, timestamps, and acoustic event awareness. The repo ships inference code, serving recipes, a subtitle web app, and fine-tuning guidance.OpenMOSS
2026-07-19
2026-05-13
2.3k stars
48
vlx-seek
A fine-grained perception vision-language model with weights and inference code for open-world grounding on edge devices.om-ai-lab
2026-08-10
2026-06-26
2.2k stars
49
hunyuanocr
HunyuanOCR is a lightweight end-to-end OCR vision-language model unifying document parsing, text spotting, information extraction and text-image translation, released with training and inference code.tencent-hunyuan
2026-07-18
2025-11-18
2.1k stars
50
joyai-echo
JD's research release for long-horizon audio-visual generation, bundling the Echo-LongVideo model and the interactive Echo-WM world model with inference code and separately downloaded checkpoints.jd-opensource
2026-08-25
2026-06-02
2.1k stars
51
fireredaudio
FireRedAudio is a general-purpose audio language model release with inference code for speech recognition, understanding, voice cloning, TTS, and editing.fireredteam
2026-08-21
2026-08-22
2k stars
52
lingbot-world-v2
LingBot-World 2.0 is an interactive world model release with 14B and 1.3B weights and inference code for long-horizon, action-driven video generation.robbyant
2026-07-15
2026-07-08
1.9k stars
53
descript-audio-codecaudioaudio-compressioncompression-algorithm
Descript's neural audio codec model, released with weights plus training and inference scripts. It compresses 44.1 kHz audio at very low bitrates while preserving fidelity.descriptinc
2026-08-26
2023-06-12
1.9k stars
54
magenta-realtimejaxmachine-learningmlx
Google's open-weights model for real-time music generation, shipped with a Python inference library, a C++ streaming engine plus example apps and DAW plugins.magenta
2026-08-26
2025-06-12
1.9k stars
55
RAVEdeep-learningneural-networkaudio
The official implementation of RAVE, a realtime neural audio variational autoencoder. It includes training, export, and realtime inference tools for timbre transfer and music generation.acids-ircam
2026-08-26
2021-06-25
1.8k stars
56
wemm-embeddingembedding-modelsmultimodalmultimodal-llm
Tencent's family of universal multimodal embedding models, released in 2B, 4B and 9B sizes, mapping text, images, videos and visual documents into a shared retrieval space.tencent
2026-08-25
2026-08-25
1.8k stars
57
mage
Lightweight multimodal model family covering image and video understanding alongside text-to-image generation, with released weights supporting research, fine-tuning, and deployment by developers.microsoft
2026-07-29
2026-06-15
1.8k stars
58
fireredtts3
FireRedTTS3 is a speech generation and editing model release supporting zero-shot cloning in 24 languages and 21 Chinese dialects, plus voice design.fireredteam
2026-08-21
2026-08-13
1.7k stars
59
vibevoice
An open expressive text-to-speech model for generating long-form, multi-speaker conversational audio such as podcasts.vibevoice-community
2026-08-08
2025-09-04
1.7k stars
60
Fun-ASRaudio-language-modelpytorchspeaker-diarization
Tongyi Lab's open LLM-based speech recognition family covering Chinese dialects and 31 languages, with FunASR, vLLM, and on-device runtimes.QwenAudio
2026-08-26
2025-12-15
1.6k stars
61
SALMONNaudioaudio-processinglarge-language-models
ByteDance's family of multimodal large language models for speech, audio and audio-visual understanding, released with model checkpoints and inference and training code.bytedance
2026-08-26
2023-08-11
1.6k stars
62
CrisperWhisperasraudiodetection
A multilingual speech recognition model for verbatim and intended transcription with precise word-level timestamps, distributed as model weights plus a Python inference package.nyrahealth
2026-08-26
2024-05-24
1.5k stars
63
dots.tts
A 2B-parameter fully continuous end-to-end autoregressive TTS model with multilingual zero-shot voice cloning and precise speech editing, released with checkpoints, inference and fine-tuning code.rednote-hilab
2026-07-21
2026-06-04
1.4k stars
64
berninivideo-editingvideo-generationimage-editing
ByteDance's unified video generation and editing framework pairing an MLLM semantic planner with a DiT renderer, released with inference code, training code, and model weights.bytedance
2026-07-15
2026-05-29
1.4k stars
65
wall-x
The official training and inference codebase for the WALL series of embodied foundation models, including LeRobot data prep, flow-matching/FAST action branches, serving and evaluation utilities.x-square-robot
2026-07-20
2025-09-04
1.3k stars
66
mini-agi
A continually learning byte-level language model that trains from scratch on an 8 GB GPU, pages expert weights from disk and keeps learning from everything it reads.volotat
2026-09-21
2026-09-19
1.3k stars
67
liftaiextractocr
An open 9B vision model from Datalab that extracts schema-conformant JSON from PDFs and images, with local HuggingFace or vLLM-based deployment options.datalab-to
2026-08-27
2026-06-03
1.3k stars
68
timestral
A family of time-series foundation models for multivariate probabilistic forecasting with lightweight inference code and leading zero-shot benchmark accuracy.mistralai
2026-10-15
2026-10-15
1.2k stars
69
giga-world-1
An open roadmap project for building world models to evaluate robot policies, sharing training and inference pipelines, model weights, datasets, and evaluation leaderboards.open-gigaai
2026-07-31
2026-06-30
1.1k stars
70
lingbot-vla-v2
A vision-language-action foundation model for real-world robot manipulation, released with pre-trained weights, training recipes and deployment code covering multiple embodiments and predictive dynamics.robbyant
2026-07-15
2026-07-07
1.1k stars
71
opdllmsmechanismon-policy-distillation
Official research code for the paper Rethinking On-Policy Distillation of Large Language Models. It provides OPD, SFT and GRPO training recipes, evaluation scripts, released checkpoints and diagnostics for reproducing the reported findings.thunlp
2026-07-15
2026-04-12
1.1k stars
72
qwen-agentworld
An open-weight language world model for general agents that simulates seven agentic environments, plus a benchmark for evaluation.qwenlm
2026-06-26
2026-06-22
1k stars
73
minimax-music3
An open-weight music generation model that creates five-minute songs with expressive vocals from lyrics and style prompts.minimax-ai
2026-08-17
2026-08-11
1k stars
74
hulu-med
An open family of medical vision-language models (4B–235B) for text, 2D/3D imaging and surgical video, released with inference and training code and strong benchmark results.zjui-ai4h
2026-07-29
2025-10-08
1k stars
75
lingbot-vision
A family of self-supervised Vision Transformer backbones for dense spatial perception, shipping pretrained weights from small to giant scales.robbyant
2026-07-09
2026-07-06
1k stars
76
open-d4rt
An unofficial PyTorch reproduction of D4RT for 4D reconstruction and tracking, with released checkpoints and eval tools.lijiaxin0111
2026-08-17
2026-05-02
1k stars
77
boogu-image
An open-source family of image generation and editing models, including Base, Turbo, and Edit variants for text-to-image, image editing, and bilingual text rendering, released with inference code and weights.boogu-project
2026-07-20
2026-06-16
1k stars
78
krea-2
The official open weights and inference code for Krea 2, a stylish text-to-image model with Raw and Turbo checkpoints.krea-ai
2026-08-07
2026-06-22
997 stars
79
lingbot-videoimage-to-videovideo-generationworld-models
An open-source mixture-of-experts video generation model for embodied intelligence, shipping weights, inference scripts, and benchmarks for text-to-video tasks.robbyant
2026-07-09
2026-07-08
983 stars
80
evoke
The official implementation of EVOKE, an interactive world model that generates long, camera-controlled video with bounded state, released with inference code, checkpoints, and a director UI.alayalab
2026-08-25
2026-08-12
978 stars
81
orca
A general world foundation model release from BAAI, providing Orca-4B weights plus text, image, and action readout evaluation code.orca-wm
2026-07-22
2026-07-04
889 stars
82
hy-embodied
Tencent Hunyuan's open embodied vision-language foundation model for physical-world agents, with roughly 30B total and 3B active parameters, released with weights and Transformers/vLLM inference code.tencent-hunyuan
2026-07-16
2026-04-05
881 stars
83
OpenCUAbenchmarkcomputer-use-agentdataset
OpenCUA is an open foundation suite for computer-use agents, offering the OpenCUA vision-language model family, the AgentNet demonstration dataset, an annotation tool, and an offline action-level benchmark.xlang-ai
2026-08-27
2025-06-21
877 stars
84
Confucius4-TTSaudiocross-lingualdeep-learning
Confucius4-TTS is an open multilingual, cross-lingual zero-shot text-to-speech model that clones a speaker's voice across 14 languages while preserving emotion and identity.netease-youdao
2026-08-27
2026-05-19
861 stars
85
doc-to-loraaiai-agenthypernetworks
Hypernetworks plus pretrained weights that instantly internalize documents into an LLM for factual recall.SakanaAI
2026-06-24
2026-02-11
844 stars
86
alayaworld
An open-source interactive long-horizon video world model with real-time camera control, prompt switching, and long-horizon memory, released with training/inference code and staged model weights.alayalab
2026-07-17
2026-07-07
807 stars
87
dreamx-world
A general-purpose interactive world model that generates long-horizon, explorable video worlds controlled by camera motion and event prompts, released with 5B checkpoints and inference code.amap-ml
2026-07-23
2026-04-10
790 stars
88
sensenova-visionmllmmllm-for-cvunified-cv
A unified vision generation model covering detection, segmentation, depth, and 3D geometry, with open weights and training pipelines.opensensenova
2026-08-13
2026-06-29
733 stars
89
MOSS-Audioaudio-captioningaudio-question-answeringaudio-understanding
An open-source audio understanding model family for speech, environmental sound and music. The release provides 4B and 8B Instruct and Thinking weights for captioning, timestamped ASR, audio QA and reasoning.OpenMOSS
2026-09-06
2026-04-11
709 stars
90
infinisplat
A research model system that reconstructs 3D Gaussian scenes from single or multiple images for novel-view rendering and local inference.zju3dv
2026-08-09
2026-07-24
680 stars
91
hy3
A 295B mixture-of-experts reasoning and agent model release with strong tool use, served via vLLM or SGLang.tencent-hunyuan
2026-08-07
2026-07-02
676 stars
92
helixworldaudio-visualgenerative-airealtime
HelixWorld is a real-time interactive audio-visual world model from Noiz AI that generates synchronized visuals and camera-aligned spatial audio as you move, released with inference code and checkpoints.noizai
2026-08-25
2026-08-03
658 stars
93
lavasr
A tiny, blazing-fast speech restoration model that upscales noisy low-sample audio into clean, crisp full-band speech.ysharma3501
2026-08-05
2026-02-10
627 stars
94
MinerU-Diffusionai4sciencediffusiondlm
A 2.5B diffusion-based document OCR model that replaces autoregressive decoding with block-level parallel decoding. It ships model weights and inference scripts for layout, text, formula and table recognition.opendatalab
2026-08-27
2026-03-13
623 stars
95
liquid-audioaudiofoundation-modelslfm2
Liquid AI's LFM2-Audio-1.5B end-to-end speech-to-speech foundation model, shipped with Python inference, demo and fine-tuning code for real-time conversation, ASR and TTS.Liquid4All
2026-08-27
2025-09-29
603 stars
96
mira
A real-time multiplayer world model of Rocket League, releasing training code, datasets, and evaluation tools for interactive video generation research.mira-wm
2026-07-09
2026-07-05
599 stars
97
llada2.x
Ant Group's LLaDA2.X series of diffusion language models, releasing 16B and 100B MoE weights with training code and an optimized dInfer/SGLang inference stack.inclusionai
2026-07-23
2025-12-11
532 stars
98
dramabox
An expressive prompt-driven text-to-speech model with voice cloning, fine-tuned on LTX-2.3 with long-form generation support.resemble-ai
2026-08-06
2026-04-16
520 stars