Spaces:
Sleeping
Sleeping
| import speech_recognition as sr | |
| import platform | |
| class VoiceHandler: | |
| def __init__(self): | |
| self.recognizer = sr.Recognizer() | |
| self.is_cloud = self._is_cloud_environment() | |
| if not self.is_cloud: | |
| # Only configure microphone settings if not in cloud | |
| self.recognizer.energy_threshold = 4000 | |
| self.recognizer.dynamic_energy_threshold = True | |
| self.recognizer.pause_threshold = 0.8 | |
| def _is_cloud_environment(self): | |
| """Check if running in a cloud environment""" | |
| # Check common cloud platform indicators | |
| return ( | |
| platform.system() == "Linux" and | |
| not self._has_audio_device() | |
| ) | |
| def _has_audio_device(self): | |
| """Check if system has an audio input device""" | |
| try: | |
| sr.Microphone() | |
| return True | |
| except (OSError, AttributeError): | |
| return False | |
| def listen_for_voice(self, language="mixed"): | |
| """ | |
| Listen for voice input in specified language. | |
| language can be: | |
| - "ar-SA" for Arabic | |
| - "en-US" for English | |
| - "mixed" for both Arabic and English | |
| """ | |
| if self.is_cloud: | |
| return "Error: Voice input is not available in cloud deployment. Please use the text input option instead." | |
| try: | |
| with sr.Microphone() as source: | |
| print("Adjusting for ambient noise...") | |
| self.recognizer.adjust_for_ambient_noise(source, duration=1) | |
| print("Listening...") | |
| audio = self.recognizer.listen(source, timeout=5, phrase_time_limit=10) | |
| print("Processing speech...") | |
| # Try Arabic first if mixed or Arabic is specified | |
| if language in ["ar-SA", "mixed"]: | |
| try: | |
| text = self.recognizer.recognize_google(audio, language="ar-SA") | |
| return text | |
| except sr.UnknownValueError: | |
| if language == "mixed": | |
| # If Arabic fails and mixed is specified, try English | |
| text = self.recognizer.recognize_google(audio, language="en-US") | |
| return text | |
| raise | |
| else: | |
| # English only | |
| text = self.recognizer.recognize_google(audio, language="en-US") | |
| return text | |
| except sr.RequestError as e: | |
| return f"Could not request results from speech service: {str(e)}" | |
| except sr.UnknownValueError: | |
| return "Could not understand audio. Please speak clearly and try again." | |
| except sr.WaitTimeoutError: | |
| return "Listening timed out. Please try again." | |
| except Exception as e: | |
| return f"Error: {str(e)}" |