meeting summary samsum LLM Model

Introduction

The bart-large-xsum-samsum model is a fine-tuned version of Facebook's BART model, specifically adjusted for abstractive text summarization tasks using the SAMSum dataset. It is designed to effectively summarize dialogues in English.

Architecture

This model leverages the BART (Bidirectional and Auto-Regressive Transformers) architecture, which is known for its seq2seq capabilities. The BART model is adept at handling text-to-text transformations, making it suitable for tasks like summarization.

Training

The model was fine-tuned on the SAMSum dataset, which is a human-annotated dialogue dataset for abstractive summarization. During training, the model achieved the following ROUGE scores:

Validation ROUGE-1: 54.3921
Validation ROUGE-2: 29.8078
Validation ROUGE-L: 45.1543
Test ROUGE-1: 53.3059
Test ROUGE-2: 28.355
Test ROUGE-L: 44.0953

Guide: Running Locally

To run the bart-large-xsum-samsum model locally, follow these steps:

Install Transformers Library: Ensure you have the transformers library installed.
```
pip install transformers
```

Load the Model: Use the transformers pipeline to load and utilize the model.

from transformers import pipeline
summarizer = pipeline("summarization", model="knkarthick/bart-large-xsum-samsum")

Summarize Text: Provide the dialogue you wish to summarize.

conversation = '''Hannah: Hey, do you have Betty's number?
Amanda: Lemme check
Amanda: Sorry, can't find it.
Amanda: Ask Larry
Amanda: He called her last time we were at the park together
Hannah: I don't know him well
Amanda: Don't be shy, he's very nice
Hannah: If you say so..
Hannah: I'd rather you texted him
Amanda: Just text him 🙂
Hannah: Urgh.. Alright
Hannah: Bye
Amanda: Bye bye'''

print(summarizer(conversation))

Cloud GPUs: For faster processing, consider using cloud-based GPU services such as AWS EC2, Google Cloud Platform, or Azure.

License

The model is available under the Apache 2.0 License.

More Related APIs in Summarization