# IndoClip : Pre Training Clip for Indonesian dataset

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findoclip-pre-training-clip-for-indonesian-dataset%2F7287%3E%5C
**Category:** Flax/JAX Projects\
**Created:** [June 24, 2021, 6:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findoclip-pre-training-clip-for-indonesian-dataset%2F7287 "2021-06-24T18:45:53Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![munggok](https://avatars.discourse-cdn.com/v4/letter/m/919ad9/32.png) [@munggok](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmunggok)%5C
**Post date:** [June 24, 2021, 6:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findoclip-pre-training-clip-for-indonesian-dataset%2F7287%2F1 "2021-06-24T18:45:53Z")

</div>

## CLIP like contrastive vision-language models for Indonesian with pre-trained text and vision models

For this project, a pre-trained image model like `ViT` and a pre-trained text model like `BERT` can be used as an image encoder and text encoder respectively.

### Model

Pre-trained ViT, BERT models can be found on the model hub. We could also use multi-lingual BERT/RoBERTa models for the Indonesian language.

### Datasets

The [WIT](https://github.com/google-research-datasets/wit) dataset can be used for this task.  
The [GEM](https://github.com/microsoft/GEM#get-dataset) dataset can also be used for the task

### Available training scripts

A training script for this will be provided soon. (see [PR](https://github.com/huggingface/transformers/pull/12285))

### (Optional) Desired project outcome

The desired outcome is to train a CLIP-like model for Indonesian language. This can be showcased with a streamlit or gradio app.

### (Optional) Challenges

This model will require some modifications to the existing models. Specifically, we will need to add projection layers in both the text and image encoder models.

---

<div class="post-metadata">

**Author:** ![gkuwanto](https://avatars.discourse-cdn.com/v4/letter/g/f4b2a3/32.png) [@gkuwanto](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fgkuwanto)%5C
**Post date:** [June 29, 2021, 5:36pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findoclip-pre-training-clip-for-indonesian-dataset%2F7287%2F3 "2021-06-29T17:36:51Z")

</div>

Hello @munggok .Are you still looking for team members for this project? I’m very interested with this project

---

<div class="post-metadata">

**Author:** ![patrickvonplaten](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/patrickvonplaten/32/2171_2.png) [@patrickvonplaten](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpatrickvonplaten)%5C
**Post date:** [June 30, 2021, 12:39pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findoclip-pre-training-clip-for-indonesian-dataset%2F7287%2F4 "2021-06-30T12:39:55Z")

</div>

Perfect, 2 is enough - let’s finalize the project 🙂

---

<div class="post-metadata">

**Author:** ![munggok](https://avatars.discourse-cdn.com/v4/letter/m/919ad9/32.png) [@munggok](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmunggok)%5C
**Post date:** [June 30, 2021, 1:01pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findoclip-pre-training-clip-for-indonesian-dataset%2F7287%2F5 "2021-06-30T13:01:51Z")

</div>

hi @gkuwanto sure, come join

@patrickvonplaten thanks patrick
