Spaces:
Sleeping
Sleeping
File size: 2,334 Bytes
c82da72 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
import speech_recognition as sr
import os
from pydub import AudioSegment
import tempfile
class VoiceHandler:
def __init__(self):
self.recognizer = sr.Recognizer()
self.recognizer.energy_threshold = 20000
self.recognizer.dynamic_energy_threshold = False
self.recognizer.pause_threshold = 0.8
def process_audio_file(self, audio_path: str, language: str) -> str:
"""Process audio file and convert to text"""
try:
# Convert audio to wav format if needed
if not audio_path.endswith('.wav'):
audio = AudioSegment.from_file(audio_path)
temp_wav = tempfile.NamedTemporaryFile(suffix='.wav', delete=False)
audio.export(temp_wav.name, format='wav')
audio_path = temp_wav.name
with sr.AudioFile(audio_path) as source:
audio = self.recognizer.record(source)
if language == "Arabic":
return self.recognizer.recognize_google(audio, language="ar-SA")
elif language == "Mixed (Arabic/English)":
try:
return self.recognizer.recognize_google(audio, language="ar-SA")
except sr.UnknownValueError:
return self.recognizer.recognize_google(audio, language="en-US")
else: # English
return self.recognizer.recognize_google(audio, language="en-US")
except sr.RequestError as e:
return f"Error: Could not request results from speech service: {str(e)}"
except sr.UnknownValueError:
return "Error: Could not understand audio. Please speak clearly and try again."
except Exception as e:
return f"Error: {str(e)}"
finally:
# Clean up temporary file if it was created
if 'temp_wav' in locals():
os.unlink(temp_wav.name)
def check_microphone_access(self) -> bool:
"""Check if microphone is accessible"""
try:
with sr.Microphone() as source:
self.recognizer.adjust_for_ambient_noise(source, duration=0.1)
return True
except (OSError, AttributeError, sr.RequestError):
return False |