# Summarization : Conversation

**URL:** <https://discuss.huggingface.co/t/summarization-conversation/8117>\
**Category:** Beginners\
**Created:** [July 7, 2021, 2:26am UTC](https://discuss.huggingface.co/t/summarization-conversation/8117 "2021-07-07T02:26:30Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![MattJan](https://avatars.discourse-cdn.com/v4/letter/m/7993a0/32.png) [@MattJan](https://discuss.huggingface.co/u/MattJan)\
**Post date:** [July 7, 2021, 2:26am UTC](https://discuss.huggingface.co/t/summarization-conversation/8117/1 "2021-07-07T02:26:30Z")

</div>

I am new in this area. Please advise some good models to generate a summary on conversation between two persons. Thank you!

---

<div class="post-metadata">

**Author:** ![lewtun](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/lewtun/32/30995_2.png) [@lewtun](https://discuss.huggingface.co/u/lewtun)\
**Post date:** [July 7, 2021, 8:51am UTC](https://discuss.huggingface.co/t/summarization-conversation/8117/2 "2021-07-07T08:51:58Z")

</div>

hey @MattJan a good place to start would be by looking at models fine-tuned on the `samsum` dataset (dialogues between two people + their summary): [Hugging Face – The AI community building the future.](https://huggingface.co/models?filter=dataset:samsum)

if you want to fine-tune your own model, a good start would be to use a pegasus model that has already be trained for summarisation, e.g. [google/pegasus-cnn\_dailymail · Hugging Face](https://huggingface.co/google/pegasus-cnn_dailymail)