Enhance documentation with detailed README and code comments

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,6 +0,0 @@
-__pycache__/
-*.egg-info/
-*.whl
-.venv/
-.pytest_cache/
-temp.txt

README.md

@@ -11,4 +11,26 @@ license: apache-2.0
 short_description: Transliteration of Kazakh & Kyrgyz into Latin and IPA
 ---
 
+# Turkic Transliteration Demo
+
+## Overview
+This Hugging Face Space demonstrates transliteration capabilities for Turkic languages, specifically Kazakh and Kyrgyz. The demo converts text between Cyrillic script, Latin script, and International Phonetic Alphabet (IPA) notation.
+
+## Features
+- **Bidirectional Transliteration**: Convert between Cyrillic and Latin scripts
+- **IPA Transcription**: Generate accurate phonetic transcriptions using IPA
+- **Language Selection**: Support for Kazakh and Kyrgyz languages
+- **Interactive Interface**: User-friendly web interface powered by Gradio
+
+## Usage
+1. Select your source and target scripts
+2. Choose the language (Kazakh or Kyrgyz)
+3. Enter or paste your text in the input field
+4. View the transliterated/transcribed output instantly
+
+## Technical Details
+This demo is powered by the `turkic-transliterate` Python package, which provides specialized transliteration tools for Turkic languages with high accuracy for linguistic research and practical applications.
+
+---
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,116 +1,21 @@
-"""
-A simple web interface to demonstrate the Turkish transliteration.
-"""
-import gradio as gr
-from turkic_translit.core import to_latin, to_ipa
-import unicodedata as ud
+# Turkic Transliteration Demo for Hugging Face Spaces
+# This application demonstrates transliteration between Cyrillic, Latin, and IPA for Turkic languages
 
+# Import the web demo UI builder from the turkic_translit package
+from turkic_translit.web_demo import build_ui
 
-def transliterate(text, lang, include_arabic, output_format):
-    if not text:
-        return "", ""
-    try:
-        if output_format == "Latin":
-            result = to_latin(text, lang, include_arabic=include_arabic)
-            format_label = "Latin"
-        else:
-            result = to_ipa(text, lang)
-            format_label = "IPA"
-        result = ud.normalize("NFC", result)
-        stats_md = (f"**Bytes** — Cyrillic : {len(text.encode('utf8'))}, "
-                    f"{format_label} : {len(result.encode('utf8'))}")
-        return result, stats_md
-    except Exception as e:
-        raise gr.Error(str(e))
+# Create the Gradio interface with default settings
+# The build_ui function configures a Gradio Interface with:
+# - Input fields for text entry
+# - Language selection (Kazakh/Kyrgyz)
+# - Script selection (Cyrillic/Latin/IPA)
+# - Real-time transliteration preview
+demo = build_ui()
 
-# Function to reset & (de)activate the Arabic checkbox when mode changes
-def _sync_arabic_checkbox(mode: str):
-    """Uncheck and disable in IPA; leave state untouched in Latin."""
-    if mode == "IPA":
-        # Forced off + greyed-out
-        return gr.update(value=False, interactive=False)
-    # Latin: keep whatever the user last chose, stay interactive
-    return gr.update(interactive=True)
-
-# Create the Gradio interface
-with gr.Blocks(title="Turkic Transliteration Demo") as demo:
-    gr.Markdown("# Turkic Transliteration Demo")
-    gr.Markdown("Enter Cyrillic text for Kazakh (kk) or Kyrgyz (ky) and see the Latin transliteration")
-    
-    with gr.Row():
-        with gr.Column():
-            input_text = gr.Textbox(
-                label="Input Text (Cyrillic)",
-                placeholder="Enter Kazakh or Kyrgyz text in Cyrillic script...",
-                lines=5
-            )
-            lang = gr.Radio(
-                ["kk", "ky"], 
-                label="Language", 
-                info="kk = Kazakh, ky = Kyrgyz",
-                value="kk"
-            )
-            output_format = gr.Radio(
-                ["Latin", "IPA"],
-                label="Output Format",
-                info="Latin = Standard Latin alphabet, IPA = International Phonetic Alphabet",
-                value="Latin"
-            )
-            include_arabic = gr.Checkbox(False, label="Also transliterate Arabic script (Latin mode only)")
-        
-        with gr.Column():
-            output_text = gr.Textbox(
-                label="Transliteration Output",
-                lines=5,
-                interactive=False
-            )
-            stats = gr.Markdown(value="")
-    
-    # Example inputs
-    examples = [
-        ["Қазақ тілі - Түркі тілдерінің бірі.", "kk", "Latin"],
-        ["Қазақ тілі - Түркі тілдерінің бірі.", "kk", "IPA"],
-        ["Кыргыз тили - Түрк тилдеринин бири.", "ky", "Latin"],
-        ["Кыргыз тили - Түрк тилдеринин бири.", "ky", "IPA"]
-    ]
-    gr.Markdown("👉 **Tip:** Click an example below to instantly fill in the fields and see the transliteration!")
-    gr.Examples(examples, [input_text, lang, output_format])
-    
-    # Live preview: update output while the user types
-    input_text.input(
-        fn=transliterate,
-        inputs=[input_text, lang, include_arabic, output_format],
-        outputs=[output_text, stats]
-    )
-
-    # Also fire when the textbox's value finishes changing (e.g., clicking an example)
-    input_text.change(
-        fn=transliterate,
-        inputs=[input_text, lang, include_arabic, output_format],
-        outputs=[output_text, stats]
-    )
-    
-    lang.change(
-        fn=transliterate,
-        inputs=[input_text, lang, include_arabic, output_format],
-        outputs=[output_text, stats]
-    )
-    
-    include_arabic.change(
-        fn=transliterate,
-        inputs=[input_text, lang, include_arabic, output_format],
-        outputs=[output_text, stats]
-    )
-    
-    output_format.change(
-        fn=transliterate,
-        inputs=[input_text, lang, include_arabic, output_format],
-        outputs=[output_text, stats]
-    )
-    # Sync Arabic checkbox with mode
-    output_format.change(_sync_arabic_checkbox, output_format, include_arabic)
-
-# Launch the app
-if __name__ == "__main__":
-    demo.queue().launch()
+# Enable queuing for better performance with multiple users
+# This prevents the server from being overwhelmed by concurrent requests
+demo.queue()
 
+# Launch the web application
+# In Hugging Face Spaces, this will make the app available to users
+demo.launch()

env.yml

@@ -1,27 +0,0 @@
-name: turkic
-channels:
-  - conda-forge
-  - defaults
-dependencies:
-  # ---------- Core binaries ----------
-  - python =3.11            # pick 3.10 or 3.11; 3.12 wheels still new
-  - icu    =73.*            # matches PyICU 2.15 wheel
-  - sentencepiece >=0.2
-  - rapidfuzz >=3.5
-  - numpy <2                # required by fasttext-wheel
-  # ---------- Build / test ----------
-  - pip
-  - pytest >=8.0
-  - packaging >=23.0        # used in tests
-  # ---------- pip-only wheels ----------
-  - pip:
-      # PyICU is handled differently for Windows vs. other platforms
-      # On Windows, we'll use the script/get_pyicu_wheel.py helper
-      - pyicu==2.15.2 ; platform_system != "Windows"
-      # language ID & vectors
-      - fasttext-wheel==0.9.2
-      # phoneme & feature extraction
-      - epitran==1.26.0
-      - git+https://github.com/dmort27/panphon.git@master#egg=panphon
-      # editable install of your package
-      - -e .

pyproject.toml

@@ -1,44 +0,0 @@
-[build-system]
-requires = ["setuptools>=68", "wheel"]
-build-backend = "setuptools.build_meta"
-
-
-[project]
-name            = "turkic_transliterate"
-version         = "0.1.0"
-description     = "Deterministic Latin and IPA transliteration for Kazakh, Kyrgyz, plus tokenizer/glue scripts."
-authors         = [ {name="Austin Wagner", email="[email protected]"} ]
-requires-python = ">=3.9"
-
-dependencies = [
-    # Core dependencies (alphabetized)
-    "epitran>=1.0,<1.27",           # 1.26.0 is the latest on PyPI
-    # Universal fasttext-wheel for all platforms and Python 3.10-3.13
-    "fasttext-wheel==0.9.2",
-    "numpy<2",
-    "packaging>=23.0",              # Used in tests/test_fasttext.py
-    "panphon>=0.20,<0.22",          # 0.21.2 is the newest published wheel
-    # Source build for non-Windows platforms
-    "PyICU>=2.15 ; sys_platform != 'win32'",
-    # Windows wheels for PyICU
-    "PyICU @ https://github.com/cgohlke/pyicu-build/releases/download/v2.15/pyicu-2.15-cp310-cp310-win_amd64.whl ; sys_platform == 'win32' and python_version == '3.10'",
-    "PyICU @ https://github.com/cgohlke/pyicu-build/releases/download/v2.15/pyicu-2.15-cp311-cp311-win_amd64.whl ; sys_platform == 'win32' and python_version == '3.11'",
-    "PyICU @ https://github.com/cgohlke/pyicu-build/releases/download/v2.15/pyicu-2.15-cp312-cp312-win_amd64.whl ; sys_platform == 'win32' and python_version == '3.12'",
-    "PyICU @ https://github.com/cgohlke/pyicu-build/releases/download/v2.15/pyicu-2.15-cp313-cp313-win_amd64.whl ; sys_platform == 'win32' and python_version == '3.13'",
-    "pytest>=8.0",                  # Test runner
-    "rapidfuzz>=3.5",
-    "rich>=13.7",                   # Color-aware logging and console output
-    "sentencepiece>=0.2.0"
-]
-
-[project.optional-dependencies]
-# winlid dependency kept for backward compatibility but empty since fasttext-wheel is now in main dependencies
-winlid = []
-
-# Development tools
-dev = ["black", "ruff"]
-# User interface dependencies
-ui = ["gradio"]
-
-[project.scripts]
-turkic-translit = "turkic_translit.cli:main"

requirements.txt

@@ -1,4 +1,6 @@
-turkic-transliterate>=0.1.1
+turkic-transliterate[ui]>=0.1.2
+
+#turkic-transliterate[ui] @ git+https://github.com/wagner-austin/turkic_transliteration.git@main
 
 # Core dependencies
 epitran>=1.0,<1.27