source languages: nl; target languages: en; OPUS readme: nl-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
Open-weight model · Translation
sanskrit-en-custom-transformer
by Praveen Kumar krpraveen/sanskrit-en-custom-transformer
A compact encoder–decoder Transformer trained from scratch on 10,000 Sanskrit–English pairs (NLU Assignment 2), with a joint SentencePiece BPE vocabulary. It is small and fast — meant to be efficient rather than to match large pretrained models.
Parameters—
Context—
Weights38.8 MB
Licensemit
AccessOpen weights
Monthly Downloads296.3k
Model Card
By Praveen Kumar, published under mit, revision e6dab729be0b.
A compact encoder–decoder Transformer trained from scratch on 10,000 Sanskrit–English pairs (NLU Assignment 2), with a joint SentencePiece BPE vocabulary. It is small and fast — meant to be efficient rather than to match large pretrained models. This is not a Transformers architecture, so it ships with a self-contained modeling.py. Files: pytorchmodel.bin (weights), spm.model (tokenizer), config.json (hyperparameters), modeling.py (model + load/translate helpers). pip install gradio first. To host it, create a Hugging Face Space (SDK: Gradio) with an app.py (the load + respond code) and a requirements.txt of torch sentencepiece huggingfacehub gradio. Trained only on the provided dataset…
Read Praveen Kumar's full model card
Sanskrit → English — Custom Transformer (trained from scratch)
A compact encoder–decoder Transformer trained from scratch on 10,000 Sanskrit–English pairs
(NLU Assignment 2), with a joint SentencePiece BPE vocabulary. It is small and fast — meant to be
efficient rather than to match large pretrained models. This is nota Transformers
architecture, so it ships with a self-containedmodeling.py.
| Parameters | ~9.4M |
| Architecture | 4+4 layer Transformer, d_model 256, 4 heads, tied embeddings |
| Vocabulary | 8,000 (joint SentencePiece BPE) |
| Test BLEU / BERTScore-F1 | 0.089 / 0.346 |
| Inference | ~7 ms/sentence |
Files: pytorch_model.bin (weights), spm.model (tokenizer), config.json (hyperparameters),
modeling.py (model + load/translate helpers).
Install
pip install torch sentencepiece huggingface_hub
Inference
from huggingface_hub import snapshot_download
import sys
d = snapshot_download("krpraveen/sanskrit-en-custom-transformer")
sys.path.insert(0, d)
from modeling import load, translate
model, sp, cfg = load(d) # add device="cuda" on a GPU
print(translate(model, sp, cfg, ["बाल: भवत्सु प्रेमं प्रकटयति ।"]))
# ['Boy displays love in you.']
Use it from an open-source chat UI (Gradio)
import gradio as gr
def respond(message, history):
return translate(model, sp, cfg, [message])[0]
gr.ChatInterface(
respond,
title="Sanskrit → English (custom Transformer)",
description="Type a Sanskrit sentence in Devanagari.",
examples=["बाल: भवत्सु प्रेमं प्रकटयति ।", "अस्तु, इदं सम्यक् दृश्यते ।"],
).launch()
pip install gradio first. To host it, create a Hugging Face Space (SDK: Gradio) with an
app.py (the load + respond code) and a requirements.txt of
torch sentencepiece huggingface_hub gradio.
Notes
Trained only on the provided dataset — no pretrained weights and no external data. Being a
from-scratch model on 10k pairs, quality is modest; a larger model or more data would help.
For higher quality see the fine-tuned IndicTrans2 model
krpraveen/indictrans2-sanskrit-en-finetuned.
Configuration
- Vocabulary size
- 8,000
Identity and Version
- Repository
- krpraveen/sanskrit-en-custom-transformer
- Publisher
- Praveen Kumar
- Task
- Translation
- Modality
- Text
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- sa, en
- Revision
- e6dab729be0bfe15e08f2008cb6f848cf8c91947
- First published
- 2026-07-04
- Last updated
- 2026-07-04
Files and Weights
6 files, 39.2 MB in total. The weights are 1 file totalling 38.8 MB in bin.
Weights1 file · 38.8 MB
Configuration2 files · 5.1 KB
Documentation1 file · 2.5 KB
Other1 file · 393.2 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| pytorch_model.bin | Weights | 38.8 MB | 2a63017d3b60 |
| config.json | Configuration | 177 B | — |
| modeling.py | Configuration | 5.0 KB | — |
| README.md | Documentation | 2.5 KB | — |
| spm.model | Other | 393.2 KB | 517d54c4e726 |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 38.8 MB
Download from Praveen Kumar
Released by Praveen Kumar through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 38.8 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About sanskrit-en-custom-transformer
Can I use sanskrit-en-custom-transformer commercially?
Yes. sanskrit-en-custom-transformer is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
Similar Models
This is the model card of NLLB-200's distilled 600M variant. Here are the metrics for that particular checkpoint. - Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper. - Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022 - Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues • Model performance measures: NLLB-200…
source languages: en; target languages: ru; OPUS readme: en-ru; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
This model can be used for translation and text-to-text generation. CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Further details about the dataset for this model can be found in the OPUS readme: en-de
hfname: kor-eng - sourcelanguages: kor - targetlanguages: eng - opusreadmeurl: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/kor-eng/README.md - originalrepo: Tatoeba-Challenge - srcconstituents: {'korHani', 'korHang', 'korLatn', 'kor'} - tgtconstituents: {'eng'} - srcmultilingual: False - tgtmultilingual: False - urlmodel: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.zip - urltestset: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.test.txt - srcalpha3: kor - tgtalpha3: eng - shortpair: ko-en - chrF2score: 0.588 - brevitypenalty: 0.9590000000000001 - reflen: 17711.0 - srcname: Korean - tgtname: English - traindate…
source languages: de; target languages: en; OPUS readme: de-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.