# Unable to train a model with training data that contains non ascii characters

**URL:** <https://forum.rasa.com/t/unable-to-train-a-model-with-training-data-that-contains-non-ascii-characters/10276>\
**Category:** Rasa Open Source\
**Created:** [May 24, 2019, 1:30am UTC](https://forum.rasa.com/t/unable-to-train-a-model-with-training-data-that-contains-non-ascii-characters/10276 "2019-05-24T01:30:38Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![andy51002000](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/andy51002000/32/1652_2.png) [@andy51002000](https://forum.rasa.com/u/andy51002000)\
**Post date:** [May 24, 2019, 1:30am UTC](https://forum.rasa.com/t/unable-to-train-a-model-with-training-data-that-contains-non-ascii-characters/10276/1 "2019-05-24T01:30:38Z")

</div>

I got the error message after I post a request to my rasa server

{ “error”: “ascii” }

My Training data

language: zh

pipeline:

- name: tokenizer\_whitespace
- name: intent\_entity\_featurizer\_regex
- name: ner\_crf
- name: ner\_synonyms
- name: intent\_featurizer\_count\_vectors
- name: intent\_classifier\_tensorflow\_embedding data: |

## intent:wifi\_not\_working

- 我 的 電腦 WIFI 打不開
- 我 的 WIFI 不能用
- 我 的 WIFI 有問題
- 我 不能 用 WIFI

## intent:find\_repair\_center

- 如何 找到 東京維修處
- 如何 找到 東京都維修處
- 如何 找到 維修中心
- 維修中心 在 哪裡
- 最近 的 維修中心 在 哪裡

I found if I remove round brackets “(” and “)”, everything works fine. I really need them to let Rasa know what entities are, so I cannot just remove. Anyone has idea to fix this problem?

---

<div class="post-metadata">

**Author:** ![BlankRain](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/blankrain/32/3042_2.png) [@BlankRain](https://forum.rasa.com/u/BlankRain)\
**Post date:** [May 24, 2019, 8:04am UTC](https://forum.rasa.com/t/unable-to-train-a-model-with-training-data-that-contains-non-ascii-characters/10276/2 "2019-05-24T08:04:47Z")

</div>

maybe you need this one: [GitHub - crownpku/Rasa\_NLU\_Chi: Turn Chinese natural language into structured data 中文自然语言理解](https://github.com/crownpku/Rasa_NLU_Chi)