Correction of the sample codes in README.md

[sefeoglu]

Hello,
There are some mistakes in your code samples in the README.

1. There is a mistake in the line of the REBEL example code below:

extracted_text = triplet_extractor.tokenizer.batch_decode(triplet_extractor("Punta Cana is a resort town in the municipality of Higuey, in La Altagracia Province, the eastern most province of the Dominican Republic", return_tensors=True, return_text=False)[0]["generated_token_ids"]["output_ids"])

The code line below gives : TypeError: 'list' object cannot be interpreted as an integer:
It should be like :

extracted_text = triplet_extractor.tokenizer.batch_decode(triplet_extractor("Punta Cana is a resort town in the municipality of Higuey, in La Altagracia Province, the eastern most province of the Dominican Republic", return_tensors=True, return_text=False)[0]["generated_token_ids"]["output_ids"][0])

2. The second mistake is in the spaCy example:
   The line below gives the TypeError: add_pipe() got an unexpected keyword argument 'config'

nlp.add_pipe("rebel", after="senter", config={
    'device':0, # Number of the GPU, -1 if want to use CPU
    'model_name':'Babelscape/rebel-large'} # Model used, will default to 'Babelscape/rebel-large' if not given
    )

Could you correct your samples in the Readme?
Thanks in advance.
Bests,

[LittlePea13]

Hi @sefeoglu thanks for bringing these two issues.

The first one has to do with a change on the transformers library, there is some inconsistency between the version in the requirements with the actual version of the library. I will try to update the requirements to a more recent transformers version and make sure that the code on the readme/repo works with it.

Regarding the second problem, I believe it comes from your end. Do you have an updated version of spaCy? I have no issues running the spaCy script with the latest version. Perhaps you can give me a bit more info in which version you are using.

[sefeoglu]

Thanks for your reply.
The second one was coming from my spaCy version.

[LittlePea13]

Fixed the first issue in the latest commit. It was due a change in the output of the pipeline component.