DSatishchandra commited on
Commit
67436ec
1 Parent(s): 49e2d43

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +10 -6
app.py CHANGED
@@ -2,9 +2,12 @@ import gradio as gr
2
  import speech_recognition as sr
3
  from gtts import gTTS
4
  import os
5
- from playsound import playsound
6
  from transformers import pipeline
7
 
 
 
 
8
  # Initialize recognizer for speech recognition
9
  recognizer = sr.Recognizer()
10
 
@@ -30,7 +33,7 @@ def process_order(order):
30
  def recognize_speech(audio):
31
  try:
32
  # If audio is from file, use SpeechRecognition to convert speech to text
33
- if isinstance(audio, str): # Audio file input
34
  with sr.AudioFile(audio) as source:
35
  audio_data = recognizer.record(source)
36
  text = recognizer.recognize_google(audio_data)
@@ -45,8 +48,9 @@ def recognize_speech(audio):
45
  tts = gTTS(text=response, lang='en')
46
  tts.save("response.mp3")
47
 
48
- # Play the MP3 response using playsound
49
- playsound("response.mp3")
 
50
 
51
  return response
52
  except Exception as e:
@@ -58,8 +62,8 @@ def create_gradio_interface():
58
  with gr.Blocks() as demo:
59
  gr.Markdown("## AI Voice Bot for Food Ordering")
60
 
61
- # Audio Input: User speaks into microphone or uploads a file
62
- audio_input = gr.Audio(type="file", label="Speak to the bot (Upload or Record Audio)")
63
 
64
  # Display the bot's response after recognition
65
  output_text = gr.Textbox(label="Bot Response")
 
2
  import speech_recognition as sr
3
  from gtts import gTTS
4
  import os
5
+ import pygame # Use pygame for playing audio
6
  from transformers import pipeline
7
 
8
+ # Initialize pygame for audio playback
9
+ pygame.mixer.init()
10
+
11
  # Initialize recognizer for speech recognition
12
  recognizer = sr.Recognizer()
13
 
 
33
  def recognize_speech(audio):
34
  try:
35
  # If audio is from file, use SpeechRecognition to convert speech to text
36
+ if isinstance(audio, str): # Audio file input (filepath)
37
  with sr.AudioFile(audio) as source:
38
  audio_data = recognizer.record(source)
39
  text = recognizer.recognize_google(audio_data)
 
48
  tts = gTTS(text=response, lang='en')
49
  tts.save("response.mp3")
50
 
51
+ # Play the MP3 response using pygame
52
+ pygame.mixer.music.load("response.mp3")
53
+ pygame.mixer.music.play()
54
 
55
  return response
56
  except Exception as e:
 
62
  with gr.Blocks() as demo:
63
  gr.Markdown("## AI Voice Bot for Food Ordering")
64
 
65
+ # Audio Input: User speaks into microphone or uploads a file (filepath)
66
+ audio_input = gr.Audio(type="filepath", label="Speak to the bot (Upload or Record Audio)")
67
 
68
  # Display the bot's response after recognition
69
  output_text = gr.Textbox(label="Bot Response")