Update app.py

app.py

@@ -1,72 +1,56 @@
-from flask import Flask, request, jsonify, send_file
+import gradio as gr
 import speech_recognition as sr
 from deep_translator import GoogleTranslator
-
 from gtts import gTTS
-import tempfile
 import os
 
-app = Flask(__name__)
-translator = Translator()
-
-# Function to recognize speech from an audio file
-def recognize_speech(audio_file):
+# Function to convert speech to text
+def speech_to_text(audio):
     recognizer = sr.Recognizer()
-    with sr.AudioFile(audio_file) as source:
-        audio = recognizer.record(source)
+    with sr.AudioFile(audio) as source:
+        audio_data = recognizer.record(source)
     try:
-        return recognizer.recognize_google(audio, language="ps")  # Default language: Pashto
+        text = recognizer.recognize_google(audio_data, language="ur")  # Urdu speech recognition
+        return text
     except sr.UnknownValueError:
-        return "Speech not recognized"
+        return "Sorry, could not understand the audio."
     except sr.RequestError:
-        return "Speech recognition service unavailable"
+        return "Error: Could not connect to the recognition service."
 
-# Function to translate text using googletrans
-def translate_text(text, source_lang, target_lang):
-    translation = translator.translate(text, src=source_lang, dest=target_lang)
-    return translation.text
+# Function to translate text from Urdu to Pashto
+def translate_text(text):
+    try:
+        translated_text = GoogleTranslator(source="ur", target="ps").translate(text)  # Urdu to Pashto
+        return translated_text
+    except Exception as e:
+        return f"Translation Error: {e}"
 
 # Function to convert text to speech
-def text_to_speech(text, lang):
-    tts = gTTS(text, lang=lang)
-    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
-    tts.save(temp_file.name)
-    return temp_file.name
-
-# Route to handle voice input and translation
-@app.route("/translate", methods=["POST"])
-def translate_text(text, source_lang, target_lang):
+def text_to_speech(text):
     try:
-        translation = GoogleTranslator(source=source_lang, target=target_lang).translate(text)
-        return translation
+        tts = gTTS(text, lang="ps")  # Convert to Pashto speech
+        tts.save("translated_audio.mp3")
+        return "translated_audio.mp3"
     except Exception as e:
-        return f"Translation Error: {str(e)}"
-
-    
-    # Save audio file temporarily
-    temp_audio = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
-    audio_file.save(temp_audio.name)
-    
-    # Recognize speech
-    text = recognize_speech(temp_audio.name)
-    os.remove(temp_audio.name)  # Delete after processing
-
-    if text == "Speech not recognized" or text == "Speech recognition service unavailable":
-        return jsonify({"error": text}), 500
-
-    # Translate from Pashto to Urdu
-    translated_text = translate_text(text, "ps", "ur")
-
-    # Convert to speech
-    audio_path = text_to_speech(translated_text, "ur")
-
-    return jsonify({"original_text": text, "translated_text": translated_text, "audio_path": audio_path})
-
-# Route to fetch the generated audio file
-@app.route("/audio", methods=["GET"])
-def get_audio():
-    audio_path = request.args.get("file")
-    return send_file(audio_path, mimetype="audio/mp3", as_attachment=True)
-
-if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=7860, debug=True)
+        return f"TTS Error: {e}"
+
+# Main function to handle end-to-end processing
+def process_voice(audio):
+    text = speech_to_text(audio)
+    if "Error" in text:
+        return text, None
+    translated_text = translate_text(text)
+    audio_path = text_to_speech(translated_text)
+    return translated_text, audio_path
+
+# Create Gradio Interface for Hugging Face
+iface = gr.Interface(
+    fn=process_voice,
+    inputs=gr.Audio(source="microphone", type="filepath"),  
+    outputs=[gr.Textbox(label="Translated Text (Pashto)"), gr.Audio(label="Translated Speech")],
+    title="Voice-to-Voice Translator (Urdu → Pashto)",
+    description="🎤 Speak in **Urdu**, and get the **Pashto** translation along with audio output."
+)
+
+# Launch the app
+iface.launch()