Model Card for Model ID

Model Card for Fine-Tuned Pegasus Summary Generator

Model Details

Model Description

This model is a fine-tuned version of the Pegasus model for text summarization, specifically optimized for generating structured summaries from transcripts. The model has been trained to capture key points, remove redundant information, and maintain coherence in summaries.

Developed by: Akshay Choudhary
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: Transformer-based summarization model
Language(s) (NLP): English
License: [More Information Needed]
Finetuned from model [optional]: google/pegasus-large

Model Sources [optional]

Repository: https://huggingface.co/akshay9125/Transcript_Summerizer/
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Uses

Direct Use

The model can be directly used for transcript summarization in various applications, including:

Meeting and lecture transcript summarization
Podcast and interview summarization
Summarization of long-form text data

Downstream Use [optional]

he model can be fine-tuned further for:

Domain-specific summarization (e.g., medical, legal, educational transcripts)
Integration into AI-powered note-taking tool

Out-of-Scope Use

Generating highly creative or fictional content
Summarizing extremely noisy or low-quality transcripts
Generating precise legal or medical documentation without expert verification

Bias, Risks, and Limitations

The model may exhibit biases based on:

T* he dataset used for fine-tuning

The quality and clarity of input transcripts
Potential loss of nuanced context in summarization

Recommendations

Users should:

Validate summaries for critical use cases
Avoid using the model for tasks requiring absolute accuracy without human verification
Be aware of potential biases in summarization

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import PegasusForConditionalGeneration, PegasusTokenizer

tokenizer = PegasusTokenizer.from_pretrained("akshay9125/Transcript_Summerizer") model = PegasusForConditionalGeneration.from_pretrained("akshay9125/Transcript_Summerizer")

def summarize_text(text): inputs = tokenizer(text, return_tensors="pt", truncation=True, padding="longest") summary_ids = model.generate(**inputs) return tokenizer.decode(summary_ids[0], skip_special_tokens=True)

Training Details

Training Data

Dataset: Collected and preprocessed transcript datasets
Preprocessing: Removal of noise, speaker labels, and unnecessary pauses

Training Procedure

Preprocessing: Tokenization with Pegasus tokenizer
Training regime: FP16 mixed precision

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

Model size: ~568M parameters

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

Akshay Choudhary

Model Card Contact

[More Information Needed]