Config.yml for a language without two-letter code

Getting Started with Rasa
1

Hi, I am trying to look for a chatbot builder that can support any local dialect and see Rasa as a candidate. for example I want to create a chatbot that supports ‘Bicolano’ a language in the Philippines.

In the docs I saw that to train a model in any whitespace tokenizable language, this config.yml must be set like this:

language: "fr"  # your two-letter language code

pipeline:
  - name: WhitespaceTokenizer
  - name: RegexFeaturizer
  - name: LexicalSyntacticFeaturizer
  - name: CountVectorsFeaturizer
  - name: CountVectorsFeaturizer
    analyzer: "char_wb"
    min_ngram: 1
    max_ngram: 4
  - name: DIETClassifier
    epochs: 100
  - name: EntitySynonymMapper
  - name: ResponseSelector
    epochs: 100

What should I set as the language here? should I leave it as fr, can it be left blank, or can i create a unique 2-letter code?

Also how many utterances per intent would you recommend to train the model from scratch? thanks!

2

Awesome and interesting article. Great things you’ve always shared with us. Thanks. Just continue composing this kind of post.