Hindi language model

Trained with ELECTRA base size settings

Tokenization and training CoLab

Example Notebooks

This model outperforms Multilingual BERT on Hindi movie reviews / sentiment analysis (using SimpleTransformers)

You can get higher accuracy using ktrain + TensorFlow, where you can adjust learning rate and other hyperparameters: https://colab.research.google.com/drive/1mSeeSfVSOT7e-dVhPlmSsQRvpn6xC05w?usp=sharing

Question-answering on MLQA dataset: https://colab.research.google.com/drive/1i6fidh2tItf_-IDkljMuaIGmEU6HT2Ar#scrollTo=IcFoAHgKCUiQ

A smaller model (Hindi-BERT) performs better on a BBC news classification task.


The corpus is two files:

Bonus notes:

  • Adding English wiki text or parallel corpus could help with cross-lingual tasks and training



Bonus notes:

  • Created with HuggingFace Tokenizers; you can increase vocabulary size and re-train; remember to change ELECTRA vocab_size


Structure your files, with data-dir named "trainer" here

- vocab.txt
- pretrain_tfrecords
-- (all .tfrecord... files)
- models
-- modelname
--- checkpoint
--- graph.pbtxt
--- model.*


Use this process to convert an in-progress or completed ELECTRA checkpoint to a Transformers-ready model:

git clone https://github.com/huggingface/transformers
python ./transformers/src/transformers/convert_electra_original_tf_checkpoint_to_pytorch.py
from transformers import TFElectraForPreTraining
model = TFElectraForPreTraining.from_pretrained("./dir_with_pytorch", from_pt=True)

Once you have formed one directory with config.json, pytorch_model.bin, tf_model.h5, special_tokens_map.json, tokenizer_config.json, and vocab.txt on the same level, run:

transformers-cli upload directory
Downloads last month
Hosted inference API

Unable to determine this model’s pipeline type. Check the docs .