Update app.py

app.py

@@ -1,64 +1,64 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from gtts import gTTS
+import tempfile
+import os
+import docx
+from pydub import AudioSegment
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Function to extract text from docx
+def extract_text_from_docx(file):
+    doc = docx.Document(file.name)
+    return [para.text.strip() for para in doc.paragraphs if para.text.strip()]
 
+# Function to convert Urdu text to speech
+def urdu_tts(text, speed):
+    tts = gTTS(text=text, lang='ur')
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp:
+        tts.save(tmp.name)
+        audio_path = tmp.name
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    # Change speed using pydub
+    sound = AudioSegment.from_file(audio_path)
+    sound = sound.speedup(playback_speed=speed)
+    final_path = audio_path.replace(".mp3", f"_x{speed}.mp3")
+    sound.export(final_path, format="mp3")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    return final_path
 
-    messages.append({"role": "user", "content": message})
+# Gradio stateful interface
+def start_reader(file, speed):
+    lines = extract_text_from_docx(file)
+    return lines, f"کل {len(lines)} لائنیں ملی ہیں۔", 0
 
-    response = ""
+def read_line(lines, line_idx, speed):
+    if line_idx < len(lines):
+        audio_file = urdu_tts(lines[line_idx], speed)
+        return lines[line_idx], audio_file, line_idx + 1
+    else:
+        return "📘 تمام لائنیں پڑھ لی گئیں!", None, line_idx
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 📖 اردو لائن بائی لائن ریڈر")
 
-        response += token
-        yield response
+    with gr.Row():
+        file_input = gr.File(label="📁 .docx فائل اپ لوڈ کریں", file_types=['.docx'])
+        speed_slider = gr.Slider(0.5, 2.0, 1.0, step=0.1, label="🔊 رفتار")
 
+    start_button = gr.Button("🚀 فائل پڑھنا شروع کریں")
+    status = gr.Textbox(label="🔹 اسٹیٹس")
+    lines_state = gr.State()
+    index_state = gr.State()
+    
+    current_line = gr.Textbox(label="📌 موجودہ لائن", lines=2)
+    audio_output = gr.Audio(label="🎧 آڈیو")
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    next_button = gr.Button("▶️ اگلی لائن پڑھیں")
 
+    start_button.click(fn=start_reader, inputs=[file_input, speed_slider],
+                       outputs=[lines_state, status, index_state])
+    
+    next_button.click(fn=read_line, inputs=[lines_state, index_state, speed_slider],
+                      outputs=[current_line, audio_output, index_state])
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()