Meetingscript

🚀 MeetingScript

A BigBird‐Pegasus model fine‑tuned for meeting transcription summarization on the MeetingBank dataset.

🚀 Quick Start

MeetingScript is a sequence‑to‑sequence model designed to summarize long meeting transcripts. You can use it as follows:

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

# 1) Load from the Hub
tokenizer = AutoTokenizer.from_pretrained("Shaelois/MeetingScript")
model = AutoModelForSeq2SeqLM.from_pretrained("Shaelois/MeetingScript")

# 2) Summarize a long transcript
transcript = """
    Alice: Good morning everyone, let’s get started…
    Bob: I updated the design mockups…
    … (thousands of words) …
"""
inputs = tokenizer(
    transcript,
    max_length=4096,
    truncation=True,
    return_tensors="pt"
).to("cuda")

summary_ids = model.generate(
    **inputs,
    num_beams=4,
    max_length=150,
    early_stopping=True
)
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print("📝 Summary:", summary)

✨ Features

• Fine - tuned for Meeting Summarization: MeetingScript is based on google/bigbird-pegasus-large-bigpatent and fine - tuned on the MeetingBank corpus. It can handle long meeting transcripts (up to 4096 tokens) and generate concise, coherent summaries.

📦 Installation

You can load the model and tokenizer from the Hugging Face Hub as shown in the Usage section.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

# 1) Load from the Hub
tokenizer = AutoTokenizer.from_pretrained("Shaelois/MeetingScript")
model = AutoModelForSeq2SeqLM.from_pretrained("Shaelois/MeetingScript")

# 2) Summarize a long transcript
transcript = """
    Alice: Good morning everyone, let’s get started…
    Bob: I updated the design mockups…
    … (thousands of words) …
"""
inputs = tokenizer(
    transcript,
    max_length=4096,
    truncation=True,
    return_tensors="pt"
).to("cuda")

summary_ids = model.generate(
    **inputs,
    num_beams=4,
    max_length=150,
    early_stopping=True
)
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print("📝 Summary:", summary)

📚 Documentation

Model Description

MeetingScript is a sequence - to - sequence model based on google/bigbird-pegasus-large-bigpatent and fine - tuned on the MeetingBank corpus of meeting transcripts paired with human - written summaries. It is designed to take long meeting transcripts (up to 4096 tokens) and produce concise, coherent summaries.

Evaluation Results

Evaluated on the held - out test split of MeetingBank (≈ 600 transcripts), using beam search (4 beams, max_length = 600):

Model Files

• Weights & config: pytorch_model.bin, config.json
• Tokenizer: tokenizer.json, tokenizer_config.json, merges.txt, special_tokens_map.json
• Generation defaults: generation_config.json

Hub

🔗 https://github.com/kevin0437/Meeting_scripts

📄 License

This model is licensed under the Apache - 2.0 license.