Source: https://seerepo.com/r/Wan-Video/Wan2.2/built
Markdown source: https://seerepo.com/r/Wan-Video/Wan2.2/built.md
Description: Wan2.2 is a Python repo built with Lightning. It uses AI through accelerate, conformer, openai-whisper, pyworld, sentencepiece, and 14 more.

# What is Wan2.2 built with?

Wan2.2 is a Python repo built with Lightning. It uses AI through accelerate, conformer, openai-whisper, pyworld, sentencepiece, and 14 more, makes its content with imageio-ffmpeg, decord, and imageio, deploys with loguru, and uses pyarrow. It has 19,152 written lines.

Read on November 6, 2026, at commit 1ea34ff.

Repository: https://github.com/Wan-Video/Wan2.2

## Frontend

### Interface

- **[Rich](https://seerepo.com/uses/rich)**
- **[matplotlib](https://seerepo.com/uses/matplotlib)**: 1 file

## Backend

### Data

- **[pyarrow](https://seerepo.com/uses/pyarrow)**

### AI

- **[accelerate](https://seerepo.com/uses/accelerate)**
- **conformer**
- **[openai-whisper](https://seerepo.com/uses/openai-whisper)**
- **pyworld**
- **[sentencepiece](https://seerepo.com/uses/sentencepiece)**
- **[tokenizers](https://seerepo.com/uses/tokenizers)**
- **wetext**
- **[torch](https://seerepo.com/uses/torch)**: 38 files
- **[diffusers](https://seerepo.com/uses/diffusers)**: 9 files
- **[opencv-python](https://seerepo.com/uses/opencv-python)**: 7 files
- **[torchvision](https://seerepo.com/uses/torchvision)**: 6 files
- **flash-attn**: 4 files
- **[transformers](https://seerepo.com/uses/transformers)**: 3 files
- **[peft](https://seerepo.com/uses/peft)**: 2 files
- **dashscope**: 1 file
- **[librosa](https://seerepo.com/uses/librosa)**: 1 file
- **[ModelScope](https://seerepo.com/uses/modelscope)**: 1 file
- **[onnxruntime](https://seerepo.com/uses/onnxruntime)**: 1 file
- **[torchaudio](https://seerepo.com/uses/torchaudio)**: 1 file

## Support

### The base

- **Lightning**

### Content

- **imageio-ffmpeg**
- **decord**: 4 files
- **imageio**: 1 file

### Deploy

- **[loguru](https://seerepo.com/uses/loguru)**: 1 file

### Tools

- **gitpython**: 1 file

### Other

- **gdown**
- **hydra-core**
- **hyperpyyaml**
- **inflect**
- **pandas**
- **wget**
- **NumPy**: 17 files
- **tqdm**: 8 files
- **easydict**: 6 files
- **ftfy**: 1 file
- **omegaconf**: 1 file

## Other repos with a similar stack

- [mudler/LocalAI](https://seerepo.com/r/mudler/LocalAI/built): pyarrow, Lightning, matplotlib, accelerate, conformer, sentencepiece, tokenizers, torch, diffusers, opencv-python, torchvision, flash-attn, transformers, peft, librosa, ModelScope, onnxruntime, torchaudio, imageio-ffmpeg, imageio, loguru · [Compare](https://seerepo.com/compare/mudler/LocalAI/vs/Wan-Video/Wan2.2)
- [debpalash/VoiceStudio](https://seerepo.com/r/debpalash/VoiceStudio/built): pyarrow, Lightning, Rich, matplotlib, accelerate, conformer, openai-whisper, torch, diffusers, torchvision, transformers, librosa, ModelScope, onnxruntime, torchaudio, imageio-ffmpeg, loguru · [Compare](https://seerepo.com/compare/debpalash/VoiceStudio/vs/Wan-Video/Wan2.2)
- [ray-project/ray](https://seerepo.com/r/ray-project/ray/built): pyarrow, Lightning, Rich, matplotlib, accelerate, openai-whisper, sentencepiece, tokenizers, torch, diffusers, torchvision, transformers, peft, onnxruntime, torchaudio, imageio-ffmpeg, imageio · [Compare](https://seerepo.com/compare/ray-project/ray/vs/Wan-Video/Wan2.2)
- [jianchang512/pyvideotrans](https://seerepo.com/r/jianchang512/pyvideotrans/built): pyarrow, Rich, accelerate, openai-whisper, sentencepiece, torch, diffusers, transformers, peft, dashscope, librosa, ModelScope, onnxruntime, torchaudio, imageio-ffmpeg, imageio · [Compare](https://seerepo.com/compare/jianchang512/pyvideotrans/vs/Wan-Video/Wan2.2)
- [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/built): pyarrow, Rich, matplotlib, accelerate, openai-whisper, sentencepiece, torch, opencv-python, transformers, peft, librosa, torchaudio, loguru · [Compare](https://seerepo.com/compare/bojieli/ai-agent-book/vs/Wan-Video/Wan2.2)
- [hpcaitech/ColossalAI](https://seerepo.com/r/hpcaitech/ColossalAI/built): Rich, matplotlib, accelerate, sentencepiece, tokenizers, torch, diffusers, torchvision, flash-attn, transformers, peft, ModelScope, torchaudio · [Compare](https://seerepo.com/compare/hpcaitech/ColossalAI/vs/Wan-Video/Wan2.2)

## Frequently asked questions

### What language is Wan2.2 written in?

Wan2.2 is written in Python, with 19,152 written lines.

### What framework does Wan2.2 use?

Wan2.2 is built with Lightning.

### Does Wan2.2 use AI?

Yes. Wan2.2 uses AI through accelerate, conformer, openai-whisper, pyworld, sentencepiece, tokenizers, wetext, torch, diffusers, opencv-python, torchvision, flash-attn, transformers, peft, dashscope, librosa, ModelScope, onnxruntime, and torchaudio.

### What services does Wan2.2 use?

Wan2.2 uses pyarrow.

### Which repos have a stack like Wan2.2's?

The ones that share most of its stack: mudler/LocalAI, debpalash/VoiceStudio, and ray-project/ray.

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.