README.md

---
language:
- as
- bn
- gu
- hi
- mr
- ne
- or
- pa
- si
- sa
- bpy
- mai
- bh
- gom
license: apache-2.0
datasets:
- oscar
tags:
- multilingual
- albert
- masked-language-modeling
- sentence-order-prediction
- fill-mask
- xlmindic
- exbert
- nlp
widget:
- text : 'rabīndranātha ṭhākura ēphaāraēēsa (7 mē 1861 - 7 āgasṭa 1941; 25 baiśākha 1268 - 22 śrābaṇa 1348 baṅgābda) chilēna agraṇī bāṅāli [MASK], aupanyāsika, saṁgītasraṣṭā, nāṭyakāra, citrakara, chōṭagalpakāra, prābandhika, abhinētā, kaṇṭhaśilpī ō dārśanika. 1913 sālē gītāñjali kābyagranthēra iṁrēji anubādēra janya tini ēśīẏadēra madhyē sāhityē prathama [MASK] puraskāra lābha karēna.'

co2_eq_emissions:
      emissions: "28.53 in grams of CO2"
      source: "calculated using this webstie https://mlco2.github.io/impact/#compute"
      training_type: "pretraining"
      geographical_location: "NA"
      hardware_used: "TPUv3-8 for about 180 hours or 7.5 days"
---

# XLMIndic Base Uniscript

Pretrained [ALBERT](https://arxiv.org/abs/1909.11942) model on the [OSCAR](https://huggingface.co/datasets/oscar) corpus on the 14 Indo-Aryan languages. This model was pretrained after transliterating the text to [ISO-15919](https://en.wikipedia.org/wiki/ISO_15919) format using the [Aksharamukha](https://pypi.org/project/aksharamukha/)
library. A demo of Aksharamukha library is hosted [here](https://aksharamukha.appspot.com/converter)
where you can transliterate your text and use it on our model on the inference widget.

## Model description

This model has the same configuration as the [ALBERT Base v2 model](https://huggingface.co/albert-base-v2/). Specifically, this model has the following configuration:

- 12 repeating layers
- 128 embedding dimension
- 768 hidden dimension
- 12 attention heads
- 11M parameters

## Training data

This model was pretrained on the [OSCAR](https://huggingface.co/datasets/oscar) dataset which is a medium sized multilingual corpus containing text from 163 languages. We select a subset of 14 languages based on the following criteria:
 - Belongs to the [Indo-Aryan language family](https://en.wikipedia.org/wiki/Indo-Aryan_languages).
 - Uses a [Brahmic script](https://en.wikipedia.org/wiki/Brahmic_scripts).
 
These are the 14 languages we pretrain this model on:
- Assamese
- Bangla
- Bihari
- Bishnupriya Manipuri
- Goan Konkani
- Gujarati
- Hindi
- Maithili
- Marathi
- Nepali
- Oriya
- Panjabi
- Sanskrit
- Sinhala.
 
## Training procedure

### Preprocessing

The texts are transliterated to ISO-15919 format using the Aksharamukha library. Then these are tokenized using SentencePiece and a vocabulary size of 50,000. The inputs of the model are
then of the form:
```
[CLS] Sentence A [SEP] Sentence B [SEP]
```

### Training

Training objective is the same as the original ALBERT. 
.
The details of the masking procedure for each sentence are the following:
- 15% of the tokens are masked.
- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
- In the 10% remaining cases, the masked tokens are left as is.

The details of the sentence order prediction example generation procedure for each sentence are the following:
- Split the sentence into two parts A and B at a random index.
- With 50% probability swap the two parts.  

The model was pretrained on TPUv3-8 for 1M steps. We have checkpoints available every 10k steps. We will upload these in the future.

## Evaluation results
We evaluated this model on the [IndicGLUE](https://huggingface.co/datasets/indic_glue) benchmark dataset.

## Intended uses & limitations

You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=xlmindic) to look for
fine-tuned versions on a task that interests you.
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
generation you should look at model like GPT2.

### How to use

To use this model you will need to first install the [Aksharamukha](https://pypi.org/project/aksharamukha/) library.

```bash
pip install aksharamukha
```

Then you can use this model directly with a pipeline for masked language modeling:

```python
>>> from transformers import pipeline
>>> from aksharamukha import transliterate
>>> unmasker = pipeline('fill-mask', model='ibraheemmoosa/xlmindic-base-uniscript')
>>> text = "রবীন্দ্রনাথ ঠাকুর এফআরএএস (৭ মে ১৮৬১ - ৭ আগস্ট ১৯৪১; ২৫ বৈশাখ ১২৬৮ - ২২ শ্রাবণ ১৩৪৮ বঙ্গাব্দ) ছিলেন অগ্রণী বাঙালি [MASK], ঔপন্যাসিক, সংগীতস্রষ্টা, নাট্যকার, চিত্রকর, ছোটগল্পকার, প্রাবন্ধিক, অভিনেতা, কণ্ঠশিল্পী ও দার্শনিক। ১৯১৩ সালে গীতাঞ্জলি কাব্যগ্রন্থের ইংরেজি অনুবাদের জন্য তিনি এশীয়দের মধ্যে সাহিত্যে প্রথম নোবেল পুরস্কার লাভ করেন।"
>>> transliterated_text = transliterate.process('Bengali', 'ISO', text)
>>> transliterated_text
'rabīndranātha ṭhākura ēphaāraēēsa (7 mē 1861 - 7 āgasṭa 1941; 25 baiśākha 1268 - 22 śrābaṇa 1348 baṅgābda) chilēna agraṇī bāṅāli [MASK], aupanyāsika, saṁgītasraṣṭā, nāṭyakāra, citrakara, chōṭagalpakāra, prābandhika, abhinētā, kaṇṭhaśilpī ō dārśanika. 1913 sālē gītāñjali kābyagranthēra iṁrēji anubādēra janya tini ēśīẏadēra madhyē sāhityē prathama [MASK] puraskāra lābha karēna.'
>>> unmasker(transliterated_text)
[{'score': 0.39705055952072144,
  'token': 1500,
  'token_str': 'abhinētā',
  'sequence': 'rabīndranātha ṭhākura ēphaāraēēsa (7 mē 1861 - 7 āgasṭa 1941; 25 baiśākha 1268 - 22 śrābaṇa 1348 baṅgābda) chilēna agraṇī bāṅāli abhinētā, aupanyāsika, saṁgītasraṣṭā, nāṭyakāra, citrakara, chōṭagalpakāra, prābandhika, abhinētā, kaṇṭhaśilpī ō dārśanika. 1913 sālē gītāñjali kābyagranthēra iṁrēji anubādēra janya tini ēśīẏadēra madhyē sāhityē prathama nōbēla puraskāra lābha karēna.'},
 {'score': 0.20499080419540405,
  'token': 3585,
  'token_str': 'kabi',
  'sequence': 'rabīndranātha ṭhākura ēphaāraēēsa (7 mē 1861 - 7 āgasṭa 1941; 25 baiśākha 1268 - 22 śrābaṇa 1348 baṅgābda) chilēna agraṇī bāṅāli kabi, aupanyāsika, saṁgītasraṣṭā, nāṭyakāra, citrakara, chōṭagalpakāra, prābandhika, abhinētā, kaṇṭhaśilpī ō dārśanika. 1913 sālē gītāñjali kābyagranthēra iṁrēji anubādēra janya tini ēśīẏadēra madhyē sāhityē prathama nōbēla puraskāra lābha karēna.'},
 {'score': 0.1314290314912796,
  'token': 15402,
  'token_str': 'rājanētā',
  'sequence': 'rabīndranātha ṭhākura ēphaāraēēsa (7 mē 1861 - 7 āgasṭa 1941; 25 baiśākha 1268 - 22 śrābaṇa 1348 baṅgābda) chilēna agraṇī bāṅāli rājanētā, aupanyāsika, saṁgītasraṣṭā, nāṭyakāra, citrakara, chōṭagalpakāra, prābandhika, abhinētā, kaṇṭhaśilpī ō dārśanika. 1913 sālē gītāñjali kābyagranthēra iṁrēji anubādēra janya tini ēśīẏadēra madhyē sāhityē prathama nōbēla puraskāra lābha karēna.'},
 {'score': 0.060830358415842056,
  'token': 3212,
  'token_str': 'kalākāra',
  'sequence': 'rabīndranātha ṭhākura ēphaāraēēsa (7 mē 1861 - 7 āgasṭa 1941; 25 baiśākha 1268 - 22 śrābaṇa 1348 baṅgābda) chilēna agraṇī bāṅāli kalākāra, aupanyāsika, saṁgītasraṣṭā, nāṭyakāra, citrakara, chōṭagalpakāra, prābandhika, abhinētā, kaṇṭhaśilpī ō dārśanika. 1913 sālē gītāñjali kābyagranthēra iṁrēji anubādēra janya tini ēśīẏadēra madhyē sāhityē prathama nōbēla puraskāra lābha karēna.'},
 {'score': 0.035522934049367905,
  'token': 11586,
  'token_str': 'sāhityakāra',
  'sequence': 'rabīndranātha ṭhākura ēphaāraēēsa (7 mē 1861 - 7 āgasṭa 1941; 25 baiśākha 1268 - 22 śrābaṇa 1348 baṅgābda) chilēna agraṇī bāṅāli sāhityakāra, aupanyāsika, saṁgītasraṣṭā, nāṭyakāra, citrakara, chōṭagalpakāra, prābandhika, abhinētā, kaṇṭhaśilpī ō dārśanika. 1913 sālē gītāñjali kābyagranthēra iṁrēji anubādēra janya tini ēśīẏadēra madhyē sāhityē prathama nōbēla puraskāra lābha karēna.'}]
```

### Limitations and bias

Even though train on a comparatively large multilingual corpus the model may exhibit harmful Gender, Ethnic and Political bias. If you fine-tune this model on a task where these issues are important you should take special care when relying on this model.

### BibTeX entry and citation info

Coming soon!