Spaces:
Runtime error
Runtime error
| """ | |
| Hugging Face Space — Indic Language Identifier | |
| Supports 12 Indic languages + English. | |
| Uses best available model: Ensemble > CharNgram > Unicode Heuristic fallback. | |
| """ | |
| from __future__ import annotations | |
| import sys | |
| from pathlib import Path | |
| sys.path.insert(0, str(Path(__file__).parent)) | |
| import gradio as gr | |
| from src.utils.languages import LANGUAGE_REGISTRY, ALL_LANGUAGE_CODES | |
| from src.data.preprocessor import IndicTextPreprocessor | |
| from src.models.ensemble_model import EnsembleLIDModel, UnicodeHeuristicModel | |
| # ── Model Loading ───────────────────────────────────────────────────────────── | |
| preprocessor = IndicTextPreprocessor() | |
| model = None | |
| for mpath in ["./artifacts/models/ensemble.pkl", "./artifacts/models/ngram_model.pkl"]: | |
| if Path(mpath).exists(): | |
| try: | |
| import pickle | |
| with open(mpath, "rb") as f: | |
| model = pickle.load(f) | |
| print(f"✓ Loaded: {mpath}") | |
| break | |
| except Exception as e: | |
| print(f"Could not load {mpath}: {e}") | |
| if model is None: | |
| model = EnsembleLIDModel() | |
| print("⚠ No trained model found — using Unicode heuristic fallback") | |
| # ── Inference ───────────────────────────────────────────────────────────────── | |
| def predict(text: str) -> str: | |
| """Clean inference function: text in → language name out.""" | |
| if not text or not text.strip(): | |
| return "Please enter some text." | |
| processed = preprocessor.preprocess(text) | |
| if hasattr(model, "predict_with_confidence"): | |
| result = model.predict_with_confidence([processed])[0] | |
| lang = result.get("predicted_lang", "?") | |
| conf = result.get("confidence", 0.0) | |
| elif hasattr(model, "predict"): | |
| lang = model.predict([processed])[0] | |
| conf = 0.9 | |
| else: | |
| lang, conf = "eng", 0.5 | |
| info = LANGUAGE_REGISTRY.get(lang) | |
| name = info.name if info else lang | |
| native = info.native_name if info else "" | |
| script = info.script if info else "?" | |
| direction = info.direction if info else "LTR" | |
| confidence_icon = "🟢" if conf > 0.8 else "🟡" if conf > 0.6 else "🔴" | |
| return ( | |
| f"**{name}** ({native})\n\n" | |
| f"Code: `{lang}` | Script: {script} | Direction: {direction}\n\n" | |
| f"Confidence: {conf:.2%} {confidence_icon}" | |
| ) | |
| def predict_detailed(text: str) -> tuple: | |
| """Returns (result_markdown, top5_table) for the full UI.""" | |
| if not text or not text.strip(): | |
| return "Please enter some text.", None | |
| processed = preprocessor.preprocess(text) | |
| if hasattr(model, "predict_with_confidence"): | |
| result = model.predict_with_confidence([processed])[0] | |
| lang = result.get("predicted_lang", "?") | |
| conf = result.get("confidence", 0.0) | |
| top5 = result.get("top_5", []) | |
| elif hasattr(model, "predict"): | |
| lang = model.predict([processed])[0] | |
| conf = 0.9 | |
| top5 = [{"lang": lang, "probability": conf}] | |
| else: | |
| lang, conf = "eng", 0.5 | |
| top5 = [] | |
| info = LANGUAGE_REGISTRY.get(lang) | |
| confidence_icon = "🟢" if conf > 0.8 else "🟡" if conf > 0.6 else "🔴" | |
| result_md = f"""### 🎯 {info.name if info else lang} ({info.native_name if info else ''}) | |
| | | | | |
| |---|---| | |
| | Code | `{lang}` | | |
| | Script | {info.script if info else '?'} | | |
| | Direction | {info.direction if info else 'LTR'} | | |
| | Family | {info.family if info else '?'} | | |
| | Confidence | {conf:.2%} {confidence_icon} | | |
| """ | |
| table = None | |
| if top5: | |
| import pandas as pd | |
| rows = [] | |
| for t in top5: | |
| i = LANGUAGE_REGISTRY.get(t["lang"]) | |
| rows.append({ | |
| "Language": i.name if i else t["lang"], | |
| "Code": t["lang"], | |
| "Probability": f"{t['probability']:.2%}", | |
| }) | |
| table = pd.DataFrame(rows) | |
| return result_md, table | |
| # ── Sample Texts ────────────────────────────────────────────────────────────── | |
| SAMPLES = [ | |
| ["भारत एक विशाल देश है जहाँ अनेक भाषाएँ बोली जाती हैं।"], | |
| ["বাংলাদেশ এবং পশ্চিমবঙ্গে বাংলা ভাষা প্রচলিত।"], | |
| ["தமிழ் மொழி உலகின் மிகவும் பழமையான மொழிகளில் ஒன்றாகும்."], | |
| ["India is a diverse country with hundreds of languages."], | |
| ["اردو پاکستان کی قومی زبان ہے۔"], | |
| ["ಕನ್ನಡ ಭಾಷೆ ಕರ್ನಾಟಕ ರಾಜ್ಯದ ಅಧಿಕೃತ ಭಾಷೆ."], | |
| ] | |
| # ── Gradio UI ───────────────────────────────────────────────────────────────── | |
| with gr.Blocks(title="Indic Language Identifier") as demo: | |
| gr.Markdown(""" | |
| # 🔤 Indic Language Identifier | |
| Detects language from text across **12 Indic languages + English**. | |
| Powered by Unicode heuristics + CharNgram ensemble. | |
| """) | |
| with gr.Row(): | |
| with gr.Column(scale=2): | |
| text_input = gr.Textbox( | |
| label="Input Text", | |
| placeholder="Type or paste text in any supported language...", | |
| lines=5, | |
| ) | |
| with gr.Row(): | |
| clear_btn = gr.Button("Clear", variant="secondary") | |
| detect_btn = gr.Button("🔍 Detect Language", variant="primary") | |
| gr.Examples(examples=SAMPLES, inputs=text_input, label="Try a sample") | |
| with gr.Column(scale=2): | |
| result_md = gr.Markdown(label="Result") | |
| top5_table = gr.Dataframe(label="Top Predictions", visible=True) | |
| detect_btn.click(fn=predict_detailed, inputs=text_input, outputs=[result_md, top5_table]) | |
| clear_btn.click(fn=lambda: ("", None), outputs=[result_md, top5_table]) | |
| text_input.submit(fn=predict_detailed, inputs=text_input, outputs=[result_md, top5_table]) | |
| gr.Markdown("""--- | |
| **Supported languages:** Bengali · English · Gujarati · Hindi · Kannada · Malayalam · Marathi · Odia · Punjabi · Tamil · Telugu · Urdu | |
| """) | |
| if __name__ == "__main__": | |
| demo.launch() | |