spaCy-wrap: For Wrapping fine-tuned transformers in spaCy pipelines

spaCy-wrap is a minimal library intended for wrapping fine-tuned transformers from the Huggingface model hub in your spaCy pipeline allowing the inclusion of existing models within SpaCy workflows.

As for as possible it follows a similar API as spacy-transformers.

Installation

Installing spacy-wrap is simple using pip:

pip install spacy_wrap

There is no reason to update from GitHub as the version on PyPI should always be the same as on GitHub.

Example

The following shows a simple example of how you can quickly add a fine-tuned transformer model from the Huggingface model hub. In this example we will use the sentiment model by Barbieri et al. (2020) for classifying whether a tweet is positive, negative or neutral. We will add this model to a blank English pipeline:

import spacy
import spacy_wrap

nlp = spacy.blank("en")

config = {
    "doc_extension_trf_data": "clf_trf_data",  # document extention for the forward pass
    "doc_extension_prediction": "sentiment",  # document extention for the prediction
    "labels": ["negative", "neutral", "positive"],
    "model": {
        "name": "cardiffnlp/twitter-roberta-base-sentiment",  # the model name or path of huggingface model
    },
}

transformer = nlp.add_pipe("classification_transformer", config=config)

doc = nlp("spaCy is a wonderful tool")

print(doc._.clf_trf_data)
# TransformerData(wordpieces=...
print(doc._.sentiment)
# 'positive'
print(doc._.sentiment_prob)
#{'prob': array([0.004, 0.028, 0.969], dtype=float32), 'labels': ['negative', 'neutral', 'positive']}

These pipelines can also easily be applied to multiple documents using the nlp.pipe as one would expect from a spaCy component:

docs = nlp.pipe(
    [
        "I hate wrapping my own models",
        "Isn't there a tool for this?",
        "spacy-wrap is great for wrapping models",
    ]
)

for doc in docs:
    print(doc._.sentiment)
# 'negative'
# 'neutral'
# 'positive'

import spacy
import spacy_wrap

nlp = spacy.blank("da")

config = {
    "doc_extension_trf_data": "clf_trf_data",  # document extention for the forward pass
    "doc_extension_prediction": "hate_speech",  # document extention for the prediction
    "labels": ["Not hate Speech", "Hate speech"],
    "model": {
        "name": "DaNLP/da-bert-hatespeech-detection",  # the model name or path of huggingface model
    },
}

transformer = nlp.add_pipe("classification_transformer", config=config)

doc = nlp("Senile gamle idiot") # old senile idiot

doc._.clf_trf_data
# TransformerData(wordpieces=...
doc._.hate_speech
# "Hate speech"
doc._.hate_speech_prob
# {'prob': array([0.013, 0.987], dtype=float32), 'labels': ['Not hate Speech', 'Hate speech']}

📖 Documentation

💬 Where to ask questions