ne-lid 1.0.0__tar.gz

ne_lid-1.0.0/PKG-INFO

@@ -0,0 +1,68 @@
+Metadata-Version: 2.4
+Name: ne-lid
+Version: 1.0.0
+Summary: Language identification for Northeast Indian languages
+Author-email: MWire Labs <connect@mwirelabs.com>
+Project-URL: Homepage, https://mwirelabs.com
+Project-URL: HuggingFace, https://huggingface.co/MWirelabs/ne-lid
+Keywords: language-identification,nlp,northeast-india,low-resource,fasttext
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: License :: Free To Use But Restricted
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: fasttext-wheel>=0.9.2
+Requires-Dist: huggingface-hub>=0.20.0
+
+# ne-lid
+
+Language identification for Northeast Indian languages.
+
+**11 languages · 99.09% accuracy · fastText · CC-BY-4.0**
+
+## Install
+
+```bash
+pip install ne-lid
+```
+
+## Usage
+
+```python
+from ne_lid import NELID
+
+model = NELID()  # downloads from HuggingFace on first run
+
+# Single prediction
+result = model.predict('Ki paidbah shnong ki la ia shim bynta')
+print(result)  # {'lang': 'kha', 'score': 0.9999}
+
+# Top-3 predictions
+results = model.predict('Ka sngi ka lieh', k=3)
+print(results)
+
+# List supported languages
+model.languages()
+```
+
+## Supported Languages
+
+| Code | Language | Accuracy |
+|------|----------|----------|
+| asm | Assamese | 100% |
+| brx | Bodo | 99% |
+| eng | English | 98% |
+| grt | Garo | 100% |
+| hin | Hindi | 97% |
+| kha | Khasi | 99% |
+| trp | Kokborok | 100% |
+| mni | Meitei | 100% |
+| lus | Mizo | 99% |
+| nag | Nagamese | 100% |
+| njz | Nyishi | 99% |
+
+Overall test accuracy: **99.09%**
+
+## Links
+- [HuggingFace](https://huggingface.co/MWirelabs/ne-lid)
+- [MWire Labs](https://mwirelabs.com)

ne_lid-1.0.0/README.md

@@ -0,0 +1,52 @@
+# ne-lid
+
+Language identification for Northeast Indian languages.
+
+**11 languages · 99.09% accuracy · fastText · CC-BY-4.0**
+
+## Install
+
+```bash
+pip install ne-lid
+```
+
+## Usage
+
+```python
+from ne_lid import NELID
+
+model = NELID()  # downloads from HuggingFace on first run
+
+# Single prediction
+result = model.predict('Ki paidbah shnong ki la ia shim bynta')
+print(result)  # {'lang': 'kha', 'score': 0.9999}
+
+# Top-3 predictions
+results = model.predict('Ka sngi ka lieh', k=3)
+print(results)
+
+# List supported languages
+model.languages()
+```
+
+## Supported Languages
+
+| Code | Language | Accuracy |
+|------|----------|----------|
+| asm | Assamese | 100% |
+| brx | Bodo | 99% |
+| eng | English | 98% |
+| grt | Garo | 100% |
+| hin | Hindi | 97% |
+| kha | Khasi | 99% |
+| trp | Kokborok | 100% |
+| mni | Meitei | 100% |
+| lus | Mizo | 99% |
+| nag | Nagamese | 100% |
+| njz | Nyishi | 99% |
+
+Overall test accuracy: **99.09%**
+
+## Links
+- [HuggingFace](https://huggingface.co/MWirelabs/ne-lid)
+- [MWire Labs](https://mwirelabs.com)

ne_lid-1.0.0/ne_lid/__init__.py

@@ -0,0 +1,4 @@
+from .model import NELID, LANGUAGES
+
+__version__ = "1.0.0"
+__all__ = ["NELID", "LANGUAGES"]

ne_lid-1.0.0/ne_lid/model.py

@@ -0,0 +1,41 @@
+import fasttext
+import os
+from huggingface_hub import hf_hub_download
+
+MODEL_REPO = "MWirelabs/ne-lid"
+MODEL_FILE = "ne_lid.bin"
+
+LANGUAGES = {
+    "asm": "Assamese",
+    "brx": "Bodo",
+    "eng": "English",
+    "grt": "Garo",
+    "hin": "Hindi",
+    "kha": "Khasi",
+    "trp": "Kokborok",
+    "mni": "Meitei",
+    "lus": "Mizo",
+    "nag": "Nagamese (Naga)",
+    "njz": "Nyishi",
+}
+
+class NELID:
+    def __init__(self):
+        print("Loading NE-LID...")
+        model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE)
+        self.model = fasttext.load_model(model_path)
+        print("Ready.")
+
+    def predict(self, text: str, k: int = 1):
+        text = text.strip().replace("\n", " ")
+        labels, scores = self.model.predict(text, k=k)
+        results = [
+            {"lang": l.replace("__label__", ""), "score": round(float(s), 4)}
+            for l, s in zip(labels, scores)
+        ]
+        return results if k > 1 else results[0]
+
+    @staticmethod
+    def languages():
+        for code, name in LANGUAGES.items():
+            print(f"  {code}  {name}")

ne_lid-1.0.0/ne_lid.egg-info/PKG-INFO

@@ -0,0 +1,68 @@
+Metadata-Version: 2.4
+Name: ne-lid
+Version: 1.0.0
+Summary: Language identification for Northeast Indian languages
+Author-email: MWire Labs <connect@mwirelabs.com>
+Project-URL: Homepage, https://mwirelabs.com
+Project-URL: HuggingFace, https://huggingface.co/MWirelabs/ne-lid
+Keywords: language-identification,nlp,northeast-india,low-resource,fasttext
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: License :: Free To Use But Restricted
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: fasttext-wheel>=0.9.2
+Requires-Dist: huggingface-hub>=0.20.0
+
+# ne-lid
+
+Language identification for Northeast Indian languages.
+
+**11 languages · 99.09% accuracy · fastText · CC-BY-4.0**
+
+## Install
+
+```bash
+pip install ne-lid
+```
+
+## Usage
+
+```python
+from ne_lid import NELID
+
+model = NELID()  # downloads from HuggingFace on first run
+
+# Single prediction
+result = model.predict('Ki paidbah shnong ki la ia shim bynta')
+print(result)  # {'lang': 'kha', 'score': 0.9999}
+
+# Top-3 predictions
+results = model.predict('Ka sngi ka lieh', k=3)
+print(results)
+
+# List supported languages
+model.languages()
+```
+
+## Supported Languages
+
+| Code | Language | Accuracy |
+|------|----------|----------|
+| asm | Assamese | 100% |
+| brx | Bodo | 99% |
+| eng | English | 98% |
+| grt | Garo | 100% |
+| hin | Hindi | 97% |
+| kha | Khasi | 99% |
+| trp | Kokborok | 100% |
+| mni | Meitei | 100% |
+| lus | Mizo | 99% |
+| nag | Nagamese | 100% |
+| njz | Nyishi | 99% |
+
+Overall test accuracy: **99.09%**
+
+## Links
+- [HuggingFace](https://huggingface.co/MWirelabs/ne-lid)
+- [MWire Labs](https://mwirelabs.com)

ne_lid-1.0.0/ne_lid.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+README.md
+pyproject.toml
+ne_lid/__init__.py
+ne_lid/model.py
+ne_lid.egg-info/PKG-INFO
+ne_lid.egg-info/SOURCES.txt
+ne_lid.egg-info/dependency_links.txt
+ne_lid.egg-info/requires.txt
+ne_lid.egg-info/top_level.txt

ne_lid-1.0.0/ne_lid.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

ne_lid-1.0.0/ne_lid.egg-info/requires.txt

@@ -0,0 +1,2 @@
+fasttext-wheel>=0.9.2
+huggingface-hub>=0.20.0

ne_lid-1.0.0/ne_lid.egg-info/top_level.txt

@@ -0,0 +1 @@
+ne_lid

ne_lid-1.0.0/pyproject.toml

@@ -0,0 +1,25 @@
+[build-system]
+requires = ["setuptools>=61", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "ne-lid"
+version = "1.0.0"
+description = "Language identification for Northeast Indian languages"
+readme = "README.md"
+authors = [{ name = "MWire Labs", email = "connect@mwirelabs.com" }]
+keywords = ["language-identification", "nlp", "northeast-india", "low-resource", "fasttext"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "License :: Free To Use But Restricted",
+]
+requires-python = ">=3.8"
+dependencies = [
+    "fasttext-wheel>=0.9.2",
+    "huggingface-hub>=0.20.0",
+]
+
+[project.urls]
+Homepage = "https://mwirelabs.com"
+HuggingFace = "https://huggingface.co/MWirelabs/ne-lid"

ne_lid-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+