Spaces:
Sleeping
Sleeping
Update voice_handler.py
Browse files- voice_handler.py +15 -16
voice_handler.py
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
import speech_recognition as sr
|
| 2 |
-
from typing import Optional
|
| 3 |
|
| 4 |
class VoiceHandler:
|
| 5 |
def __init__(self):
|
|
@@ -10,40 +9,34 @@ class VoiceHandler:
|
|
| 10 |
self.permission_granted = False
|
| 11 |
|
| 12 |
def check_microphone_access(self) -> bool:
|
| 13 |
-
"""Check if microphone is accessible"""
|
| 14 |
try:
|
| 15 |
with sr.Microphone() as source:
|
| 16 |
self.recognizer.adjust_for_ambient_noise(source, duration=0.1)
|
| 17 |
return True
|
| 18 |
except OSError as e:
|
| 19 |
-
print(
|
| 20 |
-
|
| 21 |
-
except AttributeError as e:
|
| 22 |
-
print(f"AttributeError: {e}. This may happen due to an issue with the 'sr.Microphone' configuration.")
|
| 23 |
-
return False
|
| 24 |
-
except sr.RequestError as e:
|
| 25 |
-
print(f"RequestError: {e}. This may happen if there's an issue with the SpeechRecognition service.")
|
| 26 |
return False
|
| 27 |
except Exception as e:
|
| 28 |
-
print(f"Unexpected error: {e}")
|
| 29 |
return False
|
| 30 |
|
| 31 |
def request_permissions(self) -> bool:
|
| 32 |
-
"""Request microphone permissions"""
|
| 33 |
try:
|
| 34 |
if self.check_microphone_access():
|
| 35 |
self.permission_granted = True
|
| 36 |
return True
|
| 37 |
-
print("Error: Could not access microphone. Please check your system or browser permissions.")
|
| 38 |
return False
|
| 39 |
except Exception as e:
|
| 40 |
-
print(f"
|
| 41 |
return False
|
| 42 |
|
| 43 |
def listen_for_voice(self, language: str = "mixed") -> str:
|
| 44 |
"""
|
| 45 |
Listen for voice input in specified language.
|
| 46 |
-
language can be:
|
| 47 |
- "ar-SA" for Arabic
|
| 48 |
- "en-US" for English
|
| 49 |
- "mixed" for both Arabic and English
|
|
@@ -62,16 +55,18 @@ class VoiceHandler:
|
|
| 62 |
return self._process_audio(audio, language)
|
| 63 |
|
| 64 |
except sr.RequestError as e:
|
| 65 |
-
return f"Could not request results from
|
| 66 |
except sr.UnknownValueError:
|
| 67 |
return "Could not understand audio. Please speak clearly and try again."
|
| 68 |
except sr.WaitTimeoutError:
|
| 69 |
return "Listening timed out. Please try again."
|
|
|
|
|
|
|
| 70 |
except Exception as e:
|
| 71 |
return f"Error: {str(e)}"
|
| 72 |
|
| 73 |
def _process_audio(self, audio, language: str) -> str:
|
| 74 |
-
"""Process audio input and convert to text"""
|
| 75 |
if language in ["ar-SA", "mixed"]:
|
| 76 |
try:
|
| 77 |
return self.recognizer.recognize_google(audio, language="ar-SA")
|
|
@@ -80,3 +75,7 @@ class VoiceHandler:
|
|
| 80 |
return self.recognizer.recognize_google(audio, language="en-US")
|
| 81 |
raise
|
| 82 |
return self.recognizer.recognize_google(audio, language="en-US")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import speech_recognition as sr
|
|
|
|
| 2 |
|
| 3 |
class VoiceHandler:
|
| 4 |
def __init__(self):
|
|
|
|
| 9 |
self.permission_granted = False
|
| 10 |
|
| 11 |
def check_microphone_access(self) -> bool:
|
| 12 |
+
"""Check if microphone is accessible."""
|
| 13 |
try:
|
| 14 |
with sr.Microphone() as source:
|
| 15 |
self.recognizer.adjust_for_ambient_noise(source, duration=0.1)
|
| 16 |
return True
|
| 17 |
except OSError as e:
|
| 18 |
+
print("OSError: No Default Input Device Available. This may occur if the microphone is not connected or accessible.")
|
| 19 |
+
print(f"Details: {str(e)}")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
return False
|
| 21 |
except Exception as e:
|
| 22 |
+
print(f"Unexpected error while accessing microphone: {str(e)}")
|
| 23 |
return False
|
| 24 |
|
| 25 |
def request_permissions(self) -> bool:
|
| 26 |
+
"""Request microphone permissions."""
|
| 27 |
try:
|
| 28 |
if self.check_microphone_access():
|
| 29 |
self.permission_granted = True
|
| 30 |
return True
|
|
|
|
| 31 |
return False
|
| 32 |
except Exception as e:
|
| 33 |
+
print(f"Error requesting permissions: {str(e)}")
|
| 34 |
return False
|
| 35 |
|
| 36 |
def listen_for_voice(self, language: str = "mixed") -> str:
|
| 37 |
"""
|
| 38 |
Listen for voice input in specified language.
|
| 39 |
+
language can be:
|
| 40 |
- "ar-SA" for Arabic
|
| 41 |
- "en-US" for English
|
| 42 |
- "mixed" for both Arabic and English
|
|
|
|
| 55 |
return self._process_audio(audio, language)
|
| 56 |
|
| 57 |
except sr.RequestError as e:
|
| 58 |
+
return f"Could not request results from speech service: {str(e)}"
|
| 59 |
except sr.UnknownValueError:
|
| 60 |
return "Could not understand audio. Please speak clearly and try again."
|
| 61 |
except sr.WaitTimeoutError:
|
| 62 |
return "Listening timed out. Please try again."
|
| 63 |
+
except OSError as e:
|
| 64 |
+
return "OSError: No Default Input Device Available. Please check your microphone connection."
|
| 65 |
except Exception as e:
|
| 66 |
return f"Error: {str(e)}"
|
| 67 |
|
| 68 |
def _process_audio(self, audio, language: str) -> str:
|
| 69 |
+
"""Process audio input and convert to text."""
|
| 70 |
if language in ["ar-SA", "mixed"]:
|
| 71 |
try:
|
| 72 |
return self.recognizer.recognize_google(audio, language="ar-SA")
|
|
|
|
| 75 |
return self.recognizer.recognize_google(audio, language="en-US")
|
| 76 |
raise
|
| 77 |
return self.recognizer.recognize_google(audio, language="en-US")
|
| 78 |
+
|
| 79 |
+
# Usage example:
|
| 80 |
+
# voice_handler = VoiceHandler()
|
| 81 |
+
# print(voice_handler.listen_for_voice(language="en-US"))
|