# Build a news summarizer
**URL:**
**Author:**  [@lewtun](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flewtun)%5C
**Post date:** [November 10, 2021, 4:46pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-a-news-summarizer%2F11572%2F1 "2021-11-10T16:46:29Z")
### Description
A common data science task for many business is to be able to condense the news about their products or services into short summaries. The goal of this task is to fine-tune a model to automatically summarise news articles, ideally in a domain that is of interest to you!
### Model(s)
There are various summarisation models on the Hub that have been fine-tuned on the famous CNN/Dailymail dataset. These provide a good starting point for performing domain adaptation:
- [google/pegasus-cnn\_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail)
- [google/roberta2roberta\_L-24\_cnn\_daily\_mail](https://huggingface.co/google/roberta2roberta_L-24_cnn_daily_mail)
There are also other summarization models that are worth investigating:
- [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn)
### Datasets
Using the `summarization` filter on the [Hugging Face Hub](https://huggingface.co/datasets?task_ids=task_ids:summarization&sort=downloads) gives a good list of datasets to start from.
### Challenges
[Explain whether the task is feasible with a single T4 GPU (what we get from AWS), does the data need a lot of preprocessing, are there ethical considerations etc]
### Desired project outcomes
- Create a Streamlit or Gradio app on [๐ค Spaces](https://huggingface.co/spaces) that can summarize news articles, either from their text or from a given URL.
- Donโt forget to push all your models and datasets to the Hub so others can build on them!
### Additional resources
Here are some existing spaces as inspiration:
- [https://huggingface.co/spaces/chinhon/News\_Summarizer](https://huggingface.co/spaces/chinhon/News_Summarizer)
- [https://huggingface.co/spaces/benthecoder/news-summarizer](https://huggingface.co/spaces/benthecoder/news-summarizer)
### Discord channel
To chat and organise with other people interested in this project, head over to our [Discord](http://xwo7x.mjt.lu/lnk/CAAAAkdkZwAAAAAAAAAAALG-MTEAAYCr4H8AAAAAAAyFyQBhjpnimM4rcE5DT5ibCUtRT96tWwAMh8Y/15/U6BYNMNDksyyGG4jgtzPKQ/aHR0cHM6Ly9odWdnaW5nZmFjZS5jby9qb2luL2Rpc2NvcmQ) and:
- Follow the instructions on the `#join-course` channel
- Join the `#new-summarizer` channel
Just make sure you comment here to indicate that youโll be contributing to this project ๐
---
**Author:**  [@Alifarsi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FAlifarsi)%5C
**Post date:** [November 15, 2021, 7:27pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-a-news-summarizer%2F11572%2F2 "2021-11-15T19:27:12Z")
Hi Lewis, I am interested in working on a text summarizer as my course project. How can I join this project? - Ali
---
**Author:**  [@lewtun](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flewtun)%5C
**Post date:** [November 15, 2021, 9:23pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-a-news-summarizer%2F11572%2F3 "2021-11-15T21:23:37Z")
Hi @Alifarsi you can check out the Discord channel I created (see the project description) and get started with finding a suitable dataset / model for this task ๐
---
**Author:**  [@aozorahime](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Faozorahime)%5C
**Post date:** [November 17, 2021, 1:54pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-a-news-summarizer%2F11572%2F4 "2021-11-17T13:54:53Z")
Is there any slot for this project?
---
**Author:**  [@lewtun](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flewtun)%5C
**Post date:** [November 17, 2021, 4:15pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-a-news-summarizer%2F11572%2F5 "2021-11-17T16:15:42Z")
Hey @aozorahime I suggest checking with the existing team in the Discord channel. If itโs full I can create a new team for you and others ๐
---
**Author:**  [@Saiteja](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSaiteja)%5C
**Post date:** [November 18, 2021, 3:03pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-a-news-summarizer%2F11572%2F6 "2021-11-18T15:03:31Z")
Interested , let me know any one is creating team, will join !
---
**Author:**  [@lewtun](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flewtun)%5C
**Post date:** [November 18, 2021, 9:25pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-a-news-summarizer%2F11572%2F7 "2021-11-18T21:25:03Z")
Hey @Saiteja you can check out if the team is full in the Discord channel. If itโs already 4 people, I can create a new team for you and others ๐
---
**Author:**  [@Saiteja](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSaiteja)%5C
**Post date:** [November 19, 2021, 5:23am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbuild-a-news-summarizer%2F11572%2F8 "2021-11-19T05:23:13Z")
Thank you @lewtun !