Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,70 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- as
|
4 |
+
- bn
|
5 |
+
- brx
|
6 |
+
- doi
|
7 |
+
- en
|
8 |
+
- gom
|
9 |
+
- gu
|
10 |
+
- hi
|
11 |
+
- kn
|
12 |
+
- ks
|
13 |
+
- ka
|
14 |
+
- mai
|
15 |
+
- ml
|
16 |
+
- mr
|
17 |
+
- mni
|
18 |
+
- mnb
|
19 |
+
- ne
|
20 |
+
- or
|
21 |
+
- pa
|
22 |
+
- sa
|
23 |
+
- sat
|
24 |
+
- sd
|
25 |
+
- snd
|
26 |
+
- ta
|
27 |
+
- te
|
28 |
+
- ur
|
29 |
+
language_details: >-
|
30 |
+
asm_Beng, ben_Beng, brx_Deva, doi_Deva, eng_Latn, gom_Deva, guj_Gujr,
|
31 |
+
hin_Deva, kan_Knda, kas_Arab, kas_Deva, mai_Deva, mal_Mlym, mar_Deva,
|
32 |
+
mni_Beng, mni_Mtei, npi_Deva, ory_Orya, pan_Guru, san_Deva, sat_Olck,
|
33 |
+
snd_Arab, snd_Deva, tam_Taml, tel_Telu, urd_Arab
|
34 |
+
tags:
|
35 |
+
- indictrans
|
36 |
+
- translation
|
37 |
+
- ai4bharat
|
38 |
+
- multilingual
|
39 |
license: mit
|
40 |
+
datasets:
|
41 |
+
- flores-200
|
42 |
+
metrics:
|
43 |
+
- bleu
|
44 |
+
- chrf
|
45 |
+
- chrf++
|
46 |
+
- comet
|
47 |
+
inference: false
|
48 |
---
|
49 |
+
|
50 |
+
# IndicTrans
|
51 |
+
|
52 |
+
This is the model card of IndicTrans2 En-Indic 1.1B variant.
|
53 |
+
|
54 |
+
Here are the [metrics](https://drive.google.com/drive/folders/1lOOdaU0VdRSBgJEsNav5zC7wwLBis9NI?usp=sharing) for that particular checkpoint.
|
55 |
+
|
56 |
+
Please refer to `Appendix D: Model Card` of our [preprint](https://arxiv.org/abs/2305.16307) for further details on model training, intended use, data, metrics, limitations and recommendations.
|
57 |
+
|
58 |
+
|
59 |
+
### Citation
|
60 |
+
|
61 |
+
If you consider using our work then please cite using:
|
62 |
+
|
63 |
+
```
|
64 |
+
@article{ai4bharat2023indictrans2,
|
65 |
+
title = {IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages},
|
66 |
+
author = {AI4Bharat and Jay Gala and Pranjal A. Chitale and Raghavan AK and Sumanth Doddapaneni and Varun Gumma and Aswanth Kumar and Janki Nawale and Anupama Sujatha and Ratish Puduppully and Vivek Raghavan and Pratyush Kumar and Mitesh M. Khapra and Raj Dabre and Anoop Kunchukuttan},
|
67 |
+
year = {2023},
|
68 |
+
journal = {arXiv preprint arXiv: 2305.16307}
|
69 |
+
}
|
70 |
+
```
|