Update app.py

app.py

@@ -1,132 +1,122 @@
 import sympy as sp
+import gradio as gr
 import speech_recognition as sr
 from gtts import gTTS
 import os
-import gradio as gr
-
-# Function to convert speech to text using CMU Sphinx
-def voice_to_text_from_microphone(audio=None):
-    recognizer = sr.Recognizer()
-
-    # If audio file is provided, use it. Otherwise, record from the microphone.
-    if audio:
-        # Using uploaded audio file
-        with sr.AudioFile(audio) as source:
-            audio_data = recognizer.record(source)
-    else:
-        # Using the default microphone as the audio source
-        with sr.Microphone() as source:
-            print("Please speak a math expression...")
-            recognizer.adjust_for_ambient_noise(source)
-            audio_data = recognizer.listen(source)
+import re
 
-    try:
-        # Using CMU Sphinx for offline recognition
-        text = recognizer.recognize_sphinx(audio_data)
-        print(f"Recognized text: {text}")
-        return text
-    except sr.UnknownValueError:
-        return "Sorry, I could not understand the audio."
-    except sr.RequestError:
-        return "Could not request results from Sphinx service."
-
-# Function to map speech to mathematical symbols
-def convert_speech_to_math(text):
-    # Mapping words to math operators
-    mapping = {
-        "plus": "+",
-        "minus": "-",
-        "times": "*",
-        "divided by": "/",
-        "squared": "**2",
-        "cube": "**3",
-        "square root of": "sqrt",
-        "integrate": "integrate",
-        "derivative of": "diff",
-        "factorial of": "factorial",
-        "log of": "log",
-        "e to the power of": "exp",
-        "sin of": "sin",
-        "cos of": "cos",
-        "tan of": "tan",
-        "logarithm of": "log"
-    }
-
-    # Replace speech terms with math symbols
-    for word, symbol in mapping.items():
-        text = text.replace(word, symbol)
-
-    # Return the updated expression
-    return text
-
-# Function to process the math expression using SymPy
+# Function to process math queries using sympy
 def process_math(query):
     try:
         # Clean up the input by removing unnecessary spaces
-        query = query.replace(" ", "")  # Removing extra spaces
-
+        query = query.replace(" ", "")  # Removing extra spaces around operators or parentheses
+        
         # Try to process the query using sympy
         expr = sp.sympify(query)
+
+        # Basic operations handled automatically by sympy
         result = expr
 
         # Convert the result to speech and save as mp3
         result_text = f"The result is: {result}"
         tts = gTTS(result_text, lang="en")
         tts.save("response.mp3")
-
-        # Return the result text and audio file path
+        
+        # Return the result text for display and audio for listening
         return result_text, "response.mp3"
     except Exception as e:
         return f"Error: Unable to process the query. Please check the syntax. Error: {e}", None
 
-# Gradio interface function to handle the input
-def calculator(text_input=None, audio=None):
-    # Check if an audio file is provided, then process it
-    if audio:
-        query = voice_to_text_from_microphone(audio)
-        if query.lower() == "sorry, i could not understand the audio.":
-            return query, None
+# Function to handle voice input (speech-to-text)
+def voice_to_text(audio):
+    recognizer = sr.Recognizer()
+    try:
+        with sr.AudioFile(audio) as source:
+            audio_data = recognizer.record(source)
+            text = recognizer.recognize_google(audio_data)
+            return text
+    except Exception as e:
+        return f"Error in voice recognition: {e}"
+
+# Mapping words to their corresponding numerical values
+word_to_num = {
+    "one": 1, "two": 2, "three": 3, "four": 4, "five": 5,
+    "six": 6, "seven": 7, "eight": 8, "nine": 9, "ten": 10,
+    "eleven": 11, "twelve": 12, "thirteen": 13, "fourteen": 14,
+    "fifteen": 15, "sixteen": 16, "seventeen": 17, "eighteen": 18,
+    "nineteen": 19, "twenty": 20, "thirty": 30, "forty": 40,
+    "fifty": 50, "sixty": 60, "seventy": 70, "eighty": 80, "ninety": 90,
+    "hundred": 100, "thousand": 1000
+}
+
+# Function to convert speech input into valid math expressions
+def convert_speech_to_math(text):
+    # Replace words with correct math functions (e.g., "factorial" -> "factorial()")
+    text = text.lower()
 
-        print(f"Original Query (Audio): {query}")
+    # Handle factorial, permutation, combinations, log, etc.
+    text = re.sub(r'factorial of (\w+)', lambda m: f'factorial({word_to_num.get(m.group(1), m.group(1))})', text)
+    text = re.sub(r'permutation of (\d+), (\d+)', r'permutation(\1, \2)', text)
+    text = re.sub(r'combinations of (\d+), (\d+)', r'combinations(\1, \2)', text)
+    text = re.sub(r'log of (\d+)', r'log(\1)', text)
 
-        # Convert speech to math expression
-        query = convert_speech_to_math(query)
-        print(f"Converted Math Expression: {query}")
-    
+    # Handle calculus terms like differentiation, integration, limit
+    text = re.sub(r'differentiate (.+)', r'diff(\1, x)', text)
+    text = re.sub(r'integrate (.+)', r'integrate(\1, x)', text)
+    text = re.sub(r'limit of (.+)', r'limit(\1, x, 0)', text)
+
+    # Handle trigonometric functions
+    text = re.sub(r'sin of (.+)', r'sin(\1)', text)
+    text = re.sub(r'cos of (.+)', r'cos(\1)', text)
+    text = re.sub(r'tan of (.+)', r'tan(\1)', text)
+
+    # Handle inverse trigonometric functions
+    text = re.sub(r'asin of (.+)', r'asin(\1)', text)
+    text = re.sub(r'acos of (.+)', r'acos(\1)', text)
+    text = re.sub(r'atan of (.+)', r'atan(\1)', text)
+
+    # Handle matrix-related terms
+    text = re.sub(r'matrix (\[.*\])', r'Matrix(\1)', text)
+
+    # Ensure all recognized functions are in the correct format
+    text = re.sub(r'(\w+)\s*\(', r'\1(', text)  # Remove spaces before parentheses
+
+    # If there's any common mis-formatting, clean it
+    return text
+
+# Main function to handle input and process it for math calculation (text or voice)
+def calculator(audio=None, text_input=None):
+    if audio:
+        query = voice_to_text(audio)
+        print(f"Voice Input Detected: {query}")  # Debugging: Print detected voice input
+        query = convert_speech_to_math(query)  # Convert the voice input into valid math expression
     elif text_input:
-        # If text input is provided directly
         query = text_input
-        print(f"Original Query (Text): {query}")
+        print(f"Text Input: {query}")  # Debugging: Print detected text input
     else:
         return "No valid input provided.", None
 
-    # Process the math query
+    # Process the math problem
     return process_math(query)
 
-# Define the Gradio interface
+# Gradio interface setup
 def start_interface():
+    # Gradio Interface with Voice Input, Text Input, and Output
     interface = gr.Interface(
         fn=calculator,
         inputs=[
-            gr.Textbox(
-                label="Enter a Math Expression (Text Input)",
-                placeholder="Type your math expression here..."
-            ),  # Option for text input
-            gr.Audio(
-                label="Upload an Audio File with a Math Expression",
-                type="filepath"
-            ),  # Option for uploading audio file
+            gr.Audio(type="filepath", label="Speak a Math Expression (e.g., factorial(5), differentiate x squared, integrate sin(x), matrix([[1, 2], [3, 4]]) )"),  # Voice input (required)
+            gr.Textbox(label="Or Type a Math Expression (Optional)", placeholder="Type your math expression here...")  # Optional text input
         ],
         outputs=[
-            "text",  # Display the result text
+            "text",  # Show the text result
             gr.Audio(label="Listen to the result")  # Provide the audio result
         ],
         title="Advanced Math Solver",
-        description="Solve advanced math problems including factorials, permutations, combinations, logarithms, differentiation, integration, matrices, trigonometric functions, and more.",
-        theme="huggingface",  # Use Hugging Face theme
-        live=True  # Allow live updating as the user interacts
+        description="Solve advanced math problems including factorials, permutations, combinations, logarithms, differentiation, integration, matrices, trigonometric functions, and more. Use speech or text input for accessibility.",
+        live=True
     )
-
+    
     interface.launch()
 
 if __name__ == "__main__":