Instructions to use Saravananofficial/Text_Summarizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Saravananofficial/Text_Summarizer with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Saravananofficial/Text_Summarizer") model = AutoModelForSeq2SeqLM.from_pretrained("Saravananofficial/Text_Summarizer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Saravananofficial/Text_Summarizer: direct link, hf CLI and curl.
- Browser
- Download file 1.02 kB
-
https://huggingface.co/Saravananofficial/Text_Summarizer/resolve/main/README.md
- Command line
-
hf download hf://Saravananofficial/Text_Summarizer/README.md
-
curl -L -o README.md https://huggingface.co/Saravananofficial/Text_Summarizer/resolve/main/README.md
1.02 kB
| license: apache-2.0 | |
| # Text-Summarizer | |
| ## About | |
| An Abstractive text summarizer trained using lstm based sequence to sequence model with attention mechanisim. The attention model is used for generating each word of the summary conditioned on the input sentence. | |
| - Used CNN_DailyMail dataset. | |
| - Code + Deployment : https://www.youtube.com/watch?v=LFZBA99NOpU | |
| [](https://www.youtube.com/watch?v=LFZBA99NOpU) | |
| ### Training Model Overview | |
| loss graph | |
|  | |
| encoder-decoder overview | |
|  | |
| ## Conclusion | |
| - 🫶 The machine learning model to convert a text document to abstract is done successfully. | |
| - 🫶 Created a Flask app using an api call from this repository & deployed the app in heroku app. | |
| ## Deployment: | |
| - 🫶 https://text-summariser-v1.herokuapp.com/ | |