bert-restore-punctuation

✨ bert-restore-punctuation

This a bert-base-uncased model finetuned for punctuation restoration on Yelp Reviews.

The model predicts the punctuation and upper-casing of plain, lower-cased text. An example use case can be ASR output. Or other cases when text has lost punctuation.

This model is intended for direct use as a punctuation restoration model for the general English language. Alternatively, you can use this for further fine-tuning on domain-specific texts for punctuation restoration tasks.

Model restores the following punctuations -- [! ? . , - : ; ' ]

The model also restores the upper-casing of words.

---

🚋 Usage

Below is a quick way to get up and running with the model.

1. First, install the package.

pip install rpunct

1. Sample python code.

from rpunct import RestorePuncts
# The default language is 'english'
rpunct = RestorePuncts()
rpunct.punctuate("""in 2018 cornell researchers built a high-powered detector that in combination with an algorithm-driven process called ptychography set a world record
by tripling the resolution of a state-of-the-art electron microscope as successful as it was that approach had a weakness it only worked with ultrathin samples that were
a few atoms thick anything thicker would cause the electrons to scatter in ways that could not be disentangled now a team again led by david muller the samuel b eckert
professor of engineering has bested its own record by a factor of two with an electron microscope pixel array detector empad that incorporates even more sophisticated
3d reconstruction algorithms the resolution is so fine-tuned the only blurring that remains is the thermal jiggling of the atoms themselves""")
# Outputs the following:
# In 2018, Cornell researchers built a high-powered detector that, in combination with an algorithm-driven process called Ptychography, set a world record by tripling the
# resolution of a state-of-the-art electron microscope. As successful as it was, that approach had a weakness. It only worked with ultrathin samples that were a few atoms
# thick. Anything thicker would cause the electrons to scatter in ways that could not be disentangled. Now, a team again led by David Muller, the Samuel B. 
# Eckert Professor of Engineering, has bested its own record by a factor of two with an Electron microscope pixel array detector empad that incorporates even more
# sophisticated 3d reconstruction algorithms. The resolution is so fine-tuned the only blurring that remains is the thermal jiggling of the atoms themselves.

This model works on arbitrarily large text in English language and uses GPU if available.

---

📡 Training data

Here is the number of product reviews we used for finetuning the model:

We found the best convergence around 3 epochs, which is what presented here and available via a download.

---

🎯 Accuracy

The fine-tuned model obtained the following accuracy on 45,990 held-out text samples:

Below is a breakdown of the performance of the model by each label:

---

☕ Contact

Contact Daulet Nurmanbetov for questions, feedback and/or requests for similar models.

---