Downloads · 30 days
9
17% of all-time downloads
indictrans2-ory-en-v1-best
anuj1541/indictrans2-ory-en-v1-best
indictrans2-ory-en-v1-best is a translation model from anuj1541. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as other.
Frozen baseline before extended fine-tuning (10–15 epochs).
All-time downloads
52
Public
Repo size
851 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin847 MB · 99%
At a glance
- Task
- Translation
- Library
- transformers
- License
- other
- Model type
- IndicTrans
- Access
- Public
- Created
- Jul 14, 2026
- Updated
- Jul 14, 2026
- SHA
- 091a492d
Base models
Datasets
Model card
From the Hugging Face model README
IndicTrans2 Odia→English v1 (current best snapshot)
Frozen baseline before extended fine-tuning (10–15 epochs).
Load
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from IndicTransToolkit import IndicProcessor
# Tokenizer always from the official IndicTrans2 base (custom class).
# Weights from this repo.
BASE = "ai4bharat/indictrans2-indic-en-dist-200M"
REPO = "anuj1541/indictrans2-ory-en-v1"
tokenizer = AutoTokenizer.from_pretrained(BASE, trust_remote_code=True)
model = AutoModelForSeq2SeqLM.from_pretrained(REPO, trust_remote_code=True)
Eval (500 test samples)
| Metric | Score |
|---|---|
| BLEU ↑ | 62.23 |
| ChrF ↑ | 87.29 |
| METEOR ↑ | 51.28 |
| TER ↓ | 34.97 |
- Task
- Translation
- Library
- transformers
- Type
- IndicTrans
- License
- other
- Languages
- or, en
- Created
- Jul 14, 2026
- Updated
- Jul 14, 2026