Public release: attribution required under CC-BY-NC-4.0; drop planned-retrain wording
Browse files- ATTRIBUTION +19 -0
- NOTICE +23 -2
- README.md +33 -8
- SHA256SUMS +5 -4
- assets/banner.png +2 -2
- assets/banner.svg +1 -1
ATTRIBUTION
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
ATTRIBUTION REQUIRED
|
| 2 |
+
|
| 3 |
+
Any use of this model, the demo, a derivative, or a redistribution — including research and demos — must credit Sourojit Dhua (sourojitdotcom) and link to the model page:
|
| 4 |
+
https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M
|
| 5 |
+
|
| 6 |
+
CC-BY-NC-4.0 requires attribution and forbids commercial use.
|
| 7 |
+
|
| 8 |
+
Ready-to-copy credit line:
|
| 9 |
+
|
| 10 |
+
AksharaLP-MultiIndic-8M by Sourojit Dhua (sourojitdotcom) — https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M
|
| 11 |
+
|
| 12 |
+
BibTeX:
|
| 13 |
+
|
| 14 |
+
@misc{dhua_aksharalp_multiindic_8m_2026,
|
| 15 |
+
author = {Sourojit Dhua},
|
| 16 |
+
title = {AksharaLP-MultiIndic-8M},
|
| 17 |
+
year = {2026},
|
| 18 |
+
url = {https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M}
|
| 19 |
+
}
|
NOTICE
CHANGED
|
@@ -1,8 +1,29 @@
|
|
| 1 |
AksharaLP-MultiIndic-8M — Sourojit Dhua, 2026
|
| 2 |
https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M
|
| 3 |
|
| 4 |
-
Combined model-card licence: CC-BY-NC-4.0. NON-COMMERCIAL RELEASE.
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
Original Hindi word/sentence components and runtime code retain Apache-2.0 and their existing notices. They are independently available at:
|
| 8 |
https://huggingface.co/sourojitdotcom/AksharaLP-1M-v2
|
|
|
|
| 1 |
AksharaLP-MultiIndic-8M — Sourojit Dhua, 2026
|
| 2 |
https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M
|
| 3 |
|
| 4 |
+
Combined model-card licence: CC-BY-NC-4.0. NON-COMMERCIAL RELEASE. ATTRIBUTION REQUIRED.
|
| 5 |
+
|
| 6 |
+
ATTRIBUTION REQUIRED
|
| 7 |
+
|
| 8 |
+
Any use of this model, the demo, a derivative, or a redistribution — including research and demos — must credit Sourojit Dhua (sourojitdotcom) and link to the model page:
|
| 9 |
+
https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M
|
| 10 |
+
|
| 11 |
+
CC-BY-NC-4.0 requires attribution and forbids commercial use.
|
| 12 |
+
|
| 13 |
+
Ready-to-copy credit line:
|
| 14 |
+
|
| 15 |
+
AksharaLP-MultiIndic-8M by Sourojit Dhua (sourojitdotcom) — https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M
|
| 16 |
+
|
| 17 |
+
BibTeX:
|
| 18 |
+
|
| 19 |
+
@misc{dhua_aksharalp_multiindic_8m_2026,
|
| 20 |
+
author = {Sourojit Dhua},
|
| 21 |
+
title = {AksharaLP-MultiIndic-8M},
|
| 22 |
+
year = {2026},
|
| 23 |
+
url = {https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M}
|
| 24 |
+
}
|
| 25 |
+
|
| 26 |
+
The new Bengali/Telugu/Kannada/Tamil weights include Samanantar-derived Aksharantar rows. The upstream Samanantar card specifies CC-BY-NC-4.0; other publisher pages describe CC0 packaging. This release does not certify those weights as commercially clean. Preserve source attributions and applicable upstream terms. Selecting CC-BY-NC does not resolve all derivative-rights questions.
|
| 27 |
|
| 28 |
Original Hindi word/sentence components and runtime code retain Apache-2.0 and their existing notices. They are independently available at:
|
| 29 |
https://huggingface.co/sourojitdotcom/AksharaLP-1M-v2
|
README.md
CHANGED
|
@@ -25,7 +25,7 @@ metrics:
|
|
| 25 |
---
|
| 26 |
|
| 27 |
<p align="center"><img src="assets/banner.svg" alt="AksharaLP MultiIndic — five scripts, one small footprint" width="100%"/></p>
|
| 28 |
-
<p align="center"><a href="https://huggingface.co/spaces/sourojitdotcom/AksharaLP-MultiIndic-demo">Try the
|
| 29 |
|
| 30 |
# AksharaLP-MultiIndic-8M
|
| 31 |
|
|
@@ -33,7 +33,7 @@ metrics:
|
|
| 33 |
|
| 34 |
**Hindi · Bengali · Telugu · Kannada · Tamil** — familiar Roman letters in, native script out. Five independent ~989K-parameter character Transformers, a lazily loaded dictionary per language, and the already-shipped **2,770,752-parameter Hindi sentence LM**. No inference server and no GPU required for inference. This is **transliteration, not translation or a general-purpose language model**.
|
| 35 |
|
| 36 |
-
> **
|
| 37 |
|
| 38 |
<table><tr><td align="center"><h2>4.94M</h2>five word models combined</td><td align="center"><h2>7.72M</h2>with the optional Hindi LM</td><td align="center"><h2>20.55 MB</h2>all word payloads, gzip-9</td><td align="center"><h2>23.48 MB</h2>including Hindi sentence mode</td></tr></table>
|
| 39 |
|
|
@@ -197,14 +197,14 @@ Browser gzip decoding requires `DecompressionStream` support; Node uses its buil
|
|
| 197 |
|
| 198 |
## Python reference
|
| 199 |
|
| 200 |
-
Requires `numpy` and `torch`.
|
| 201 |
|
| 202 |
```python
|
| 203 |
from pathlib import Path
|
| 204 |
import sys
|
| 205 |
from huggingface_hub import snapshot_download
|
| 206 |
|
| 207 |
-
root = Path(snapshot_download('sourojitdotcom/AksharaLP-MultiIndic-8M'
|
| 208 |
sys.path.insert(0, str(root / 'python'))
|
| 209 |
from multiindic import MultiIndic
|
| 210 |
|
|
@@ -264,9 +264,34 @@ engine.load_sentence_gguf(root / 'gguf/aksharalp-hi-sentence-q8.gguf')
|
|
| 264 |
print(engine.transliterate('main theek hoon'))
|
| 265 |
```
|
| 266 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 267 |
## Licence & data
|
| 268 |
|
| 269 |
-
**Model-card licence: CC-BY-NC-4.0. This release is non-commercial.** The Bengali, Telugu, Kannada and Tamil weights contain `aks-Samanantar` Aksharantar training rows. The [current upstream Samanantar card](https://huggingface.co/datasets/ai4bharat/samanantar) states **CC-BY-NC-4.0**. Aksharantar and the publisher's Samanantar packaging page describe CC0 packaging, so provenance terms conflict; this release does **not** certify those weights as commercially clean.
|
| 270 |
|
| 271 |
| Resource | Terms / role |
|
| 272 |
|---|---|
|
|
@@ -289,7 +314,7 @@ The **Hindi components are also separately available under Apache-2.0**: [Akshar
|
|
| 289 |
|
| 290 |
**Does every language understand a sentence?** No. Only Hindi has neural sentence rescoring. Others concatenate independent word predictions, preserving text layout. Hindi rescoring cannot recover a spelling outside its candidate list.
|
| 291 |
|
| 292 |
-
**Can I use it commercially?**
|
| 293 |
|
| 294 |
**Does text leave the device?** The demo fetches local model assets from the Space when loading a language. Typed text is processed in the browser and is not sent to an inference API or telemetry service. Once the selected assets are loaded, typing needs no network. This is not a promise to avoid the initial asset download.
|
| 295 |
|
|
@@ -299,7 +324,7 @@ The **Hindi components are also separately available under Apache-2.0**: [Akshar
|
|
| 299 |
|
| 300 |
Names, ambiguous short words, unseen vocabulary, English code-switching, dialects and chat abbreviations can fail. The output must be user-reviewable; do not silently replace important legal, medical or financial text. Candidate suggestions are uncalibrated. Input encoding truncates a word after 31 Roman characters. Type-as-you-go inference is debounced; older phones and long sentences may be slow. All measured compute here is CPU, not an on-device mobile benchmark. Tiny low-bit downloads still expand to float32 arrays and large dictionary structures in RAM.
|
| 301 |
|
| 302 |
-
This
|
| 303 |
|
| 304 |
---
|
| 305 |
-
**AksharaLP · Sourojit Dhua · 2026-11-10 (IST)** ·
|
|
|
|
| 25 |
---
|
| 26 |
|
| 27 |
<p align="center"><img src="assets/banner.svg" alt="AksharaLP MultiIndic — five scripts, one small footprint" width="100%"/></p>
|
| 28 |
+
<p align="center"><a href="https://huggingface.co/spaces/sourojitdotcom/AksharaLP-MultiIndic-demo">Try the browser demo ↗</a> · <a href="#benchmarks">Measured benchmarks</a> · <a href="#gguf-containers">13 GGUF files</a> · <a href="#attribution-required">Attribution required</a> · <a href="#licence--data">Licence & data</a></p>
|
| 29 |
|
| 30 |
# AksharaLP-MultiIndic-8M
|
| 31 |
|
|
|
|
| 33 |
|
| 34 |
**Hindi · Bengali · Telugu · Kannada · Tamil** — familiar Roman letters in, native script out. Five independent ~989K-parameter character Transformers, a lazily loaded dictionary per language, and the already-shipped **2,770,752-parameter Hindi sentence LM**. No inference server and no GPU required for inference. This is **transliteration, not translation or a general-purpose language model**.
|
| 35 |
|
| 36 |
+
> **Attribution required. Non-commercial (CC-BY-NC-4.0).** Any use — including research, demos, derivatives, and redistribution — must credit **Sourojit Dhua (sourojitdotcom)** and link to this [model page](https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M). CC-BY-NC-4.0 requires attribution and forbids commercial use. The new Bengali/Telugu/Kannada/Tamil weights include Samanantar-derived Aksharantar rows; the [upstream Samanantar card](https://huggingface.co/datasets/ai4bharat/samanantar) states CC-BY-NC-4.0, so this release does **not** certify those weights as commercially clean. The Hindi word and sentence components remain independently available under Apache-2.0 in their original repositories. See [Attribution required](#attribution-required) and [Licence & data](#licence--data).
|
| 37 |
|
| 38 |
<table><tr><td align="center"><h2>4.94M</h2>five word models combined</td><td align="center"><h2>7.72M</h2>with the optional Hindi LM</td><td align="center"><h2>20.55 MB</h2>all word payloads, gzip-9</td><td align="center"><h2>23.48 MB</h2>including Hindi sentence mode</td></tr></table>
|
| 39 |
|
|
|
|
| 197 |
|
| 198 |
## Python reference
|
| 199 |
|
| 200 |
+
Requires `numpy` and `torch`. The repository is public; no Hugging Face token is required to download it. Never put a write token in browser code.
|
| 201 |
|
| 202 |
```python
|
| 203 |
from pathlib import Path
|
| 204 |
import sys
|
| 205 |
from huggingface_hub import snapshot_download
|
| 206 |
|
| 207 |
+
root = Path(snapshot_download('sourojitdotcom/AksharaLP-MultiIndic-8M'))
|
| 208 |
sys.path.insert(0, str(root / 'python'))
|
| 209 |
from multiindic import MultiIndic
|
| 210 |
|
|
|
|
| 264 |
print(engine.transliterate('main theek hoon'))
|
| 265 |
```
|
| 266 |
|
| 267 |
+
## Attribution required
|
| 268 |
+
|
| 269 |
+
**Any use of this model or demo — including research, demos, derivatives, and redistribution — must credit Sourojit Dhua (sourojitdotcom)** and link to this model page: [https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M](https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M).
|
| 270 |
+
|
| 271 |
+
This release is licensed under [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/), which **requires attribution** and **forbids commercial use**.
|
| 272 |
+
|
| 273 |
+
Ready-to-copy credit line:
|
| 274 |
+
|
| 275 |
+
```text
|
| 276 |
+
AksharaLP-MultiIndic-8M by Sourojit Dhua (sourojitdotcom) — https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M
|
| 277 |
+
```
|
| 278 |
+
|
| 279 |
+
BibTeX:
|
| 280 |
+
|
| 281 |
+
```bibtex
|
| 282 |
+
@misc{dhua_aksharalp_multiindic_8m_2026,
|
| 283 |
+
author = {Sourojit Dhua},
|
| 284 |
+
title = {AksharaLP-MultiIndic-8M},
|
| 285 |
+
year = {2026},
|
| 286 |
+
url = {https://huggingface.co/sourojitdotcom/AksharaLP-MultiIndic-8M}
|
| 287 |
+
}
|
| 288 |
+
```
|
| 289 |
+
|
| 290 |
+
The same text is in [NOTICE](NOTICE) and [ATTRIBUTION](ATTRIBUTION).
|
| 291 |
+
|
| 292 |
## Licence & data
|
| 293 |
|
| 294 |
+
**Model-card licence: CC-BY-NC-4.0. This release is non-commercial, and attribution is required.** The Bengali, Telugu, Kannada and Tamil weights contain `aks-Samanantar` Aksharantar training rows. The [current upstream Samanantar card](https://huggingface.co/datasets/ai4bharat/samanantar) states **CC-BY-NC-4.0**. Aksharantar and the publisher's Samanantar packaging page describe CC0 packaging, so provenance terms conflict; this release does **not** certify those weights as commercially clean.
|
| 295 |
|
| 296 |
| Resource | Terms / role |
|
| 297 |
|---|---|
|
|
|
|
| 314 |
|
| 315 |
**Does every language understand a sentence?** No. Only Hindi has neural sentence rescoring. Others concatenate independent word predictions, preserving text layout. Hindi rescoring cannot recover a spelling outside its candidate list.
|
| 316 |
|
| 317 |
+
**Can I use it commercially?** No. This combined release is CC-BY-NC-4.0: commercial use is not allowed, and any use must credit **Sourojit Dhua (sourojitdotcom)** with a link to this model page. Independently Apache-licensed Hindi releases remain available for Hindi-only use where their terms apply. Retain all source attributions and review applicable component terms.
|
| 318 |
|
| 319 |
**Does text leave the device?** The demo fetches local model assets from the Space when loading a language. Typed text is processed in the browser and is not sent to an inference API or telemetry service. Once the selected assets are loaded, typing needs no network. This is not a promise to avoid the initial asset download.
|
| 320 |
|
|
|
|
| 324 |
|
| 325 |
Names, ambiguous short words, unseen vocabulary, English code-switching, dialects and chat abbreviations can fail. The output must be user-reviewable; do not silently replace important legal, medical or financial text. Candidate suggestions are uncalibrated. Input encoding truncates a word after 31 Roman characters. Type-as-you-go inference is debounced; older phones and long sentences may be slow. All measured compute here is CPU, not an on-device mobile benchmark. Tiny low-bit downloads still expand to float32 arrays and large dictionary structures in RAM.
|
| 326 |
|
| 327 |
+
This release records the current artifacts. No “best in class,” general-LLM capability, sub-5-MB complete bundle, commercial-clean, or multilingual-sentence claim is made.
|
| 328 |
|
| 329 |
---
|
| 330 |
+
**AksharaLP · Sourojit Dhua (sourojitdotcom) · 2026-11-10 (IST)** · CC-BY-NC-4.0. Attribution required. Non-commercial use only.
|
SHA256SUMS
CHANGED
|
@@ -1,13 +1,14 @@
|
|
| 1 |
ef294438456f56bb1968e8725a65d841a2d0c685aa591bab663b441a860a2465 .gitattributes
|
|
|
|
| 2 |
cc97a2c4ff7723a1f25179dc7c18f676fa84191bbb36ea7d0061acaf3c102559 LICENSE
|
| 3 |
e61722325c93e58388069e84e208e43ca5b6294050676ee27194921cf453a071 LICENSE-APACHE-2.0
|
| 4 |
-
|
| 5 |
-
|
| 6 |
f6484f5caaebaf2acb68540cc2cb29402030aee22a7e45b25d37424872f769a8 aksharalp.mjs
|
| 7 |
e29d4e04be4a7235d4f2b94b6578cd580486960a7068b048e1bf6c1b1799679a assets/accuracy.png
|
| 8 |
c5378130af32052f6020b7cdc5a491aa5f1d11de763c37ee5491ba1eaef0bf49 assets/accuracy.svg
|
| 9 |
-
|
| 10 |
-
|
| 11 |
70d7aee1fe5e1e61dc7154c0aa4e33c818ff30ebbbe5d78fb5f52ba09fad1e04 assets/sizes.png
|
| 12 |
e6a92bb1337fb4997c5d657e12d0b34208d0240e006aa3eb58bce6d3a9b53bec assets/sizes.svg
|
| 13 |
f5689263059364546fe23824634183d8781defb4691f36d951fff63558f16afc config.json
|
|
|
|
| 1 |
ef294438456f56bb1968e8725a65d841a2d0c685aa591bab663b441a860a2465 .gitattributes
|
| 2 |
+
fb947d2eb60cf092d963cdceb779d082ac6eae2e8ea02ce51a0dcc334f9fa4ca ATTRIBUTION
|
| 3 |
cc97a2c4ff7723a1f25179dc7c18f676fa84191bbb36ea7d0061acaf3c102559 LICENSE
|
| 4 |
e61722325c93e58388069e84e208e43ca5b6294050676ee27194921cf453a071 LICENSE-APACHE-2.0
|
| 5 |
+
07099348c854c0a7845c83ae06d83cffdc817f40997c0ae4501a52103ea31ed7 NOTICE
|
| 6 |
+
0ce210c66b634b769c9dd1a03f0cfe6f7ca79dce1f6a8d43a5c745d83e24bc07 README.md
|
| 7 |
f6484f5caaebaf2acb68540cc2cb29402030aee22a7e45b25d37424872f769a8 aksharalp.mjs
|
| 8 |
e29d4e04be4a7235d4f2b94b6578cd580486960a7068b048e1bf6c1b1799679a assets/accuracy.png
|
| 9 |
c5378130af32052f6020b7cdc5a491aa5f1d11de763c37ee5491ba1eaef0bf49 assets/accuracy.svg
|
| 10 |
+
754e34b71d892ef137be1fffdefde88df7d811a17135efc5747e1057161452d3 assets/banner.png
|
| 11 |
+
ef1d99cabfd5b2814b3e991a6ac9a97e2089c93e76a44d500ae01ae395e87815 assets/banner.svg
|
| 12 |
70d7aee1fe5e1e61dc7154c0aa4e33c818ff30ebbbe5d78fb5f52ba09fad1e04 assets/sizes.png
|
| 13 |
e6a92bb1337fb4997c5d657e12d0b34208d0240e006aa3eb58bce6d3a9b53bec assets/sizes.svg
|
| 14 |
f5689263059364546fe23824634183d8781defb4691f36d951fff63558f16afc config.json
|
assets/banner.png
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|
assets/banner.svg
CHANGED
|
|
|
|