> For the complete documentation index, see [llms.txt](https://docs.candy-smith.com/main/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.candy-smith.com/main/word-connect-game-toolkit/word-processing-tool.md).

# Word processing tool

Find more languages here <https://github.com/hermitdave/FrequencyWords/tree/master/content/2018/en>

To clean your words from no usable or not appropriate language use this [notebook](https://colab.research.google.com/drive/1PHkvPC6DOVWJjF78QHmVTzhe8AChNm6F?usp=sharing)

* Drag your words list to Collab folder and rename to input.txt

<figure><img src="/files/CrGOv4mqMWpe7vfbT0sw" alt=""><figcaption></figcaption></figure>

* Set language in the Configuration Variables
* Optionally set Open AI API key to process words more accurately
* Press "Run All"
* Download "processed\_words.txt" or "llm\_filtered\_processed\_words.txt" if you used LLM option

<figure><img src="/files/mOwf5vUSGUkP2WuaESB5" alt=""><figcaption></figcaption></figure>

* Follow this [doc](/main/word-connect-game-toolkit/train-new-model-or-update.md) to train model with your processed txt file