Downloads · 30 days
8
8% of all-time downloads
hari31416/indictrans2-indic-en-dist-200M-ONNX-q4f16
indictrans2-indic-en-dist-200M-ONNX-q4f16 is a translation model from hari31416. Use it when you need text moved from one language to another. It is set up for onnx. The card lists the license as mit.
[!TIP] This model is part of a suite of optimized/quantized ONNX versions of the base model. Other variants in this direction: - FP32 (Full Precision / Base): hari31416/indictrans2-indic-en-dist-200M-ONNX - FP16 (Half…
Downloads · 30 days
8
8% of all-time downloads
All-time downloads
103
Public
Repo size
675 MB
Likes
0
Public
Click a slice to open those files.
.data269 MB · 88%
From the Hugging Face model README
[!TIP] This model is part of a suite of optimized/quantized ONNX versions of the base model. Other variants in this direction:
- FP32 (Full Precision / Base):
hari31416/indictrans2-indic-en-dist-200M-ONNX- FP16 (Half Precision):
hari31416/indictrans2-indic-en-dist-200M-ONNX-fp16- INT8 (Dynamic Quantization):
hari31416/indictrans2-indic-en-dist-200M-ONNX-int8- Q4F16 (4-bit Block Quantization):
hari31416/indictrans2-indic-en-dist-200M-ONNX-q4f16(Current)
ONNX-exported and quantized version of ai4bharat/indictrans2-indic-en-dist-200M
for in-browser and local edge inference.
Built for use with Transformers.js and onnxruntime-web in the browser, with fast BPE tokenizer.json files that don't require the SentencePiece WASM runtime.
These charts show overall tradeoffs, language-level parity, and category breakdown.

Compared against the FP32 ONNX oracle on the golden evaluation fixtures.
| Format | Model Size | Exact Match (Token) | Exact Match (Text) | SacreBLEU (Raw) | Latency (Mean) | Speedup vs. FP32 |
|---|---|---|---|---|---|---|
| FP32 | 1.19 GB | 100.00% | 100.00% | 100.00 | 12.2 ms | 1.000x |
| FP16 | 627.2 MB | 99.91% | 99.91% | 99.96 | 14.3 ms | 0.849x |
| INT8 | 319.7 MB | 85.64% | 85.64% | 94.34 | 10.1 ms | 1.171x |
| Q4F16 | 358.6 MB | 73.36% | 73.36% | 88.31 | 15.8 ms | 0.742x |
Exact match rates and translation quality (SacreBLEU / chrF) per language pair under this precision:
| Language Code | Total Fixtures | Token Match Rate | Text Match Rate | SacreBLEU | SacreBLEU (chrF) |
|---|---|---|---|---|---|
| eng_Latn | 1100 | 73.4% | 73.4% | 88.31 | 93.92 |
Exact match rates and translation quality grouped by category types:
| Category | Total Fixtures | Token Match Rate | Text Match Rate | SacreBLEU | SacreBLEU (chrF) |
|---|---|---|---|---|---|
| Generic | 286 | 67.1% | 67.1% | 83.93 | 91.80 |
| Lexicon | 264 | 65.9% | 65.9% | 86.83 | 92.67 |
| Numerals | 264 | 79.9% | 79.9% | 92.22 | 96.31 |
| Politics | 286 | 80.4% | 80.4% | 90.23 | 94.93 |
Here is a sample of up to 5 translation mismatches compared to the FP32 oracle. Many mismatches represent minor synonym differences or spacing variations.
মই দিল্লীলৈ বিমানৰ টিকট এখন বুক কৰিব বিচাৰো।I want to book a flight ticket to Delhi.I would like to book a flight ticket to Delhi.পেট্ৰ "লৰ মূল্য পাঁচ টকা বৃদ্ধি পাইছে।The price of petrol has been increased by five rupees.The price of petrol has been hiked by Rs.বিশ্ববিদ্যালয়খনত এখন নতুন পুথিভঁৰাল উদ্বোধন কৰা হয়।A new library was opened at the university.A new library was inaugurated at the university.স্থানীয় চৰকাৰে পথবোৰ মেৰামতি কৰি আছে।The roads are being repaired by the local government.The local government is repairing the roads.কৃত্ৰিম বুদ্ধিমত্তাই শিক্ষাৰ ক্ষেত্ৰত পৰিৱৰ্তন কঢ়িয়াই আহিছে।Artificial intelligence is changing education.Artificial intelligence is transforming education.encoder_model.onnx (and optional .onnx.data weights sidecar)decoder_model.onnx and decoder_with_past_model.onnx (share decoder_shared.onnx.data when present)translate.py — self-contained Python inference helper (see Usage below)tokenizer_src.json, tokenizer_tgt.json, tokenizer_meta.json)config.json, generation_config.json)# translate.py is included in this repo alongside the ONNX bundle.
# You can also find it (and read the full source) at:
# https://github.com/Hari31416/indictrans2-onnx-export/blob/main/src/translate.py
from translate import IndicTransONNX
# Pass a HF repo ID for automatic download, or a local bundle directory path
model = IndicTransONNX("hari31416/indictrans2-indic-en-dist-200M-ONNX-q4f16")
print(model.translate("चुनाव कौन जीतेगा?", src_lang="hin_Deva", tgt_lang="eng_Latn"))
Required packages:
pip install onnxruntime tokenizers huggingface-hub
MIT (preserved from upstream AI4Bharat).