Create app.py

app.py

@@ -0,0 +1,93 @@
+import gradio as gr
+import trafilatura
+import docling
+import torch
+import soundfile as sf
+import numpy as np
+from langdetect import detect
+from kokoro import KPipeline
+import re
+import json
+import nltk
+
+nltk.download("punkt")
+
+# Initialize KokoroTTS with default English
+kokoro_tts = KPipeline(lang_code='a')  # 'a' is for American English
+
+# Supported TTS Languages
+SUPPORTED_TTS_LANGUAGES = {
+    "en": "a",  # English (default)
+    "fr": "f",  # French
+    "hi": "h",  # Hindi
+    "it": "i",  # Italian
+    "pt": "p",  # Brazilian Portuguese
+}
+
+### 1️⃣ Fetch and Extract Content
+def fetch_content(url):
+    """Fetch and extract text from a given URL (HTML or PDF)."""
+    if url.endswith(".pdf") or "pdf" in url:
+        text = docling.extract_text(url)
+    else:
+        downloaded = trafilatura.fetch_url(url)
+        text = trafilatura.extract(downloaded, output_format="markdown", with_metadata=False)
+    return text
+
+### 2️⃣ Cleaning Function
+def extract_and_clean_text(data):
+    """Removes citations, links, markdown elements, and unnecessary sections."""
+    def clean_text(text):
+        text = re.sub(r'\[\d+\]', '', text)  # Remove citations like [2][4]
+        text = re.sub(r'http[s]?://\S+', '', text)  # Remove URLs
+        text = re.sub(r'[*_`]', '', text)  # Remove markdown formatting
+        text = re.sub(r'\n\s*\n+', '\n\n', text).strip()  # Remove excessive whitespace
+        return text
+
+    return clean_text(data)
+
+### 3️⃣ Language Detection
+def detect_language(text):
+    """Detects the language of extracted text."""
+    try:
+        lang = detect(text)
+        return lang if lang in SUPPORTED_TTS_LANGUAGES else "en"  # Default to English if not supported
+    except:
+        return "en"  # Default to English if detection fails
+
+### 4️⃣ TTS Functionality (KokoroTTS)
+def generate_audio_kokoro(text, lang):
+    """Generate speech using KokoroTTS for supported languages."""
+    lang_code = SUPPORTED_TTS_LANGUAGES.get(lang, "a")  # Default to English
+    generator = kokoro_tts(text, voice="af_bella", speed=1, split_pattern=r'\n+')
+
+    # Combine audio segments into a single file
+    audio_data = np.concatenate([audio for gs, ps, audio in generator])
+    output_file = f"audio_{lang}.wav"
+    sf.write(output_file, audio_data, 24000)  # Save as WAV file
+    return output_file
+
+### 5️⃣ Main Processing Function
+def process_url(url):
+    """Processes the URL, extracts text, detects language, and converts to audio."""
+    content = fetch_content(url)
+    cleaned_text = extract_and_clean_text(content)
+    detected_lang = detect_language(cleaned_text)
+    audio_file = generate_audio_kokoro(cleaned_text, detected_lang)
+
+    return cleaned_text, detected_lang, audio_file
+
+### 6️⃣ Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("# 🌍 Web-to-Audio Converter 🎙️")
+    
+    url_input = gr.Textbox(label="Enter URL", placeholder="https://example.com/article")
+    process_button = gr.Button("Generate Audio")
+    
+    extracted_text = gr.Markdown(label="Extracted Content")
+    detected_language = gr.Textbox(label="Detected Language")
+    full_audio_output = gr.Audio(label="Generated Audio")
+
+    process_button.click(process_url, inputs=[url_input], outputs=[extracted_text, detected_language, full_audio_output])
+
+demo.launch()