Trainin error with YAml Validation Error

Rasa Open Source
1

Hi, I am trying to fine tune a model with a custom dataset. But, while training it yields an error like this. I tried supervised_embeddings, it also doesn’t work. however, the demo bot trains okay when with the initial project with rasa init. Can someone look at it?

YamlValidationException: Failed to validate YAML. Please make sure the file is correct and all mandatory parameters are specified. Here are the errors found during validation:
  in Line 3:
      Value 'b'pretrained_embeddings_spacy'' is not a list. Value path: '/pipeline'
2

Hi, I’m assuming this is your config file? If so, can you share it?

3

Hi @fkoerner, The config file looks like this. I assume this is not correct. Can you guide what needs to be done.

image
image873×426 47.7 KB

Moreover, I have some videos in domain.yml file but looks like specifying the youtube link doesn’ work this way. My domain.yml is like this: image

This gives another error in YAMLvalidation. Do you have any idea on this well. Thanks

4

Hi, specifying the pipeline this way was deprecated in 1.8, and removed in 2. You’ll need to specify a pipeline, read more about that here.

Embedding videos like that won’t work. You’ll need to find a solution depending on your front end.