ai4bharat / MultiIndicSentenceSummarization

huggingface.co
Total runs: 24
24-hour runs: 0
7-day runs: 18
30-day runs: 18
Model's Last Updated: Abril 30 2022
text2text-generation

Introduction of MultiIndicSentenceSummarization

Model Details of MultiIndicSentenceSummarization

MultiIndicSentenceSummarization

This repository contains the IndicBART checkpoint finetuned on the 11 languages of IndicSentenceSummarization dataset. For finetuning details, see the paper .

  • Supported languages: Assamese, Bengali, Gujarati, Hindi, Marathi, Odiya, Punjabi, Kannada, Malayalam, Tamil, and Telugu. Not all of these languages are supported by mBART50 and mT5.
  • The model is much smaller than the mBART and mT5(-base) models, so less computationally expensive for decoding.
  • Trained on large Indic language corpora (431K sentences).
  • All languages, have been represented in Devanagari script to encourage transfer learning among the related languages.
Using this model in transformers
from transformers import MBartForConditionalGeneration, AutoModelForSeq2SeqLM
from transformers import AlbertTokenizer, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("ai4bharat/MultiIndicSentenceSummarization", do_lower_case=False, use_fast=False, keep_accents=True)
# Or use tokenizer = AlbertTokenizer.from_pretrained("ai4bharat/MultiIndicSentenceSummarization", do_lower_case=False, use_fast=False, keep_accents=True)
model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/MultiIndicSentenceSummarization")
# Or use model = MBartForConditionalGeneration.from_pretrained("ai4bharat/MultiIndicSentenceSummarization")

# Some initial mapping
bos_id = tokenizer._convert_token_to_id_with_added_voc("<s>")
eos_id = tokenizer._convert_token_to_id_with_added_voc("</s>")
pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>")

# To get lang_id use any of ['<2as>', '<2bn>', '<2en>', '<2gu>', '<2hi>', '<2kn>', '<2ml>', '<2mr>', '<2or>', '<2pa>', '<2ta>', '<2te>']
# First tokenize the input. The format below is how IndicBART was trained so the input should be "Sentence </s> <2xx>" where xx is the language code. Similarly, the output should be "<2yy> Sentence </s>".
inp = tokenizer("जम्मू एवं कश्मीर के अनंतनाग जिले में शनिवार को सुरक्षाबलों के साथ मुठभेड़ में दो आतंकवादियों को मार गिराया गया। </s> <2hi>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids 

# For generation. Pardon the messiness. Note the decoder_start_token_id.

model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3, num_beams=5, length_penalty=0.8, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2hi>"))

# Decode to get output strings
decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
print(decoded_output) # जम्मू एवं कश्मीरः अनंतनाग में सुरक्षाबलों के साथ मुठभेड़ में दो आतंकवादी ढेर

# Note that if your output language is not Hindi or Marathi, you should convert its script from Devanagari to the desired language using the Indic NLP Library.

Note:

If you wish to use any language written in a non-Devanagari script, then you should first convert it to Devanagari using the Indic NLP Library . After you get the output, you should convert it back into the original script.

Benchmarks

Scores on the IndicSentenceSummarization test sets are as follows:

Language Rouge-1 / Rouge-2 / Rouge-L
as 60.46 / 46.77 / 59.29
bn 51.12 / 34.91 / 49.29
gu 47.89 / 29.97 / 45.92
hi 50.7 / 28.11 / 45.34
kn 77.93 / 70.03 / 77.32
ml 67.7 / 54.42 / 66.42
mr 48.06 / 26.98 / 46.5
or 45.2 / 23.66 / 43.65
pa 55.96 / 37.2 / 52.22
ta 58.85 / 38.97 / 56.83
te 54.81 / 35.28 / 53.44
Citation

If you use this model, please cite the following paper:

@inproceedings{Kumar2022IndicNLGSM,
  title={IndicNLG Suite: Multilingual Datasets for Diverse NLG Tasks in Indic Languages},
  author={Aman Kumar and Himani Shrotriya and Prachi Sahu and Raj Dabre and Ratish Puduppully and Anoop Kunchukuttan and Amogh Mishra and Mitesh M. Khapra and Pratyush Kumar},
  year={2022},
  url = "https://arxiv.org/abs/2203.05437"
  }

Runs of ai4bharat MultiIndicSentenceSummarization on huggingface.co

24
Total runs
0
24-hour runs
0
3-day runs
18
7-day runs
18
30-day runs

More Information About MultiIndicSentenceSummarization huggingface.co Model

More MultiIndicSentenceSummarization license Visit here:

https://choosealicense.com/licenses/mit

MultiIndicSentenceSummarization huggingface.co

MultiIndicSentenceSummarization huggingface.co is an AI model on huggingface.co that provides MultiIndicSentenceSummarization's model effect (), which can be used instantly with this ai4bharat MultiIndicSentenceSummarization model. huggingface.co supports a free trial of the MultiIndicSentenceSummarization model, and also provides paid use of the MultiIndicSentenceSummarization. Support call MultiIndicSentenceSummarization model through api, including Node.js, Python, http.

MultiIndicSentenceSummarization huggingface.co Url

https://huggingface.co/ai4bharat/MultiIndicSentenceSummarization

ai4bharat MultiIndicSentenceSummarization online free

MultiIndicSentenceSummarization huggingface.co is an online trial and call api platform, which integrates MultiIndicSentenceSummarization's modeling effects, including api services, and provides a free online trial of MultiIndicSentenceSummarization, you can try MultiIndicSentenceSummarization online for free by clicking the link below.

ai4bharat MultiIndicSentenceSummarization online free url in huggingface.co:

https://huggingface.co/ai4bharat/MultiIndicSentenceSummarization

MultiIndicSentenceSummarization install

MultiIndicSentenceSummarization is an open source model from GitHub that offers a free installation service, and any user can find MultiIndicSentenceSummarization on GitHub to install. At the same time, huggingface.co provides the effect of MultiIndicSentenceSummarization install, users can directly use MultiIndicSentenceSummarization installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

MultiIndicSentenceSummarization install url in huggingface.co:

https://huggingface.co/ai4bharat/MultiIndicSentenceSummarization

Url of MultiIndicSentenceSummarization

MultiIndicSentenceSummarization huggingface.co Url

Provider of MultiIndicSentenceSummarization huggingface.co

ai4bharat
ORGANIZATIONS

Other API from ai4bharat

huggingface.co

Total runs: 1.1M
Run Growth: 656.1K
Growth Rate: 59.59%
Updated: Agosto 07 2022
huggingface.co

Total runs: 49.5K
Run Growth: 3.8K
Growth Rate: 7.58%
Updated: Dezembro 21 2022
huggingface.co

Total runs: 1.7K
Run Growth: 295
Growth Rate: 16.88%
Updated: Agosto 07 2022
huggingface.co

Total runs: 1.1K
Run Growth: -3.1K
Growth Rate: -278.75%
Updated: Março 11 2024
huggingface.co

Total runs: 223
Run Growth: -81
Growth Rate: -23.62%
Updated: Outubro 18 2024
huggingface.co

Total runs: 24
Run Growth: 9
Growth Rate: 42.86%
Updated: Outubro 18 2024
huggingface.co

Total runs: 18
Run Growth: 7
Growth Rate: 30.43%
Updated: Outubro 18 2024
huggingface.co

Total runs: 8
Run Growth: -3
Growth Rate: -11.54%
Updated: Outubro 18 2024
huggingface.co

Total runs: 3
Run Growth: 17
Growth Rate: 56.67%
Updated: Outubro 18 2024
huggingface.co

Total runs: 3
Run Growth: 10
Growth Rate: 40.00%
Updated: Outubro 18 2024