Code_Projects/voicy at main · AsSakina/Code_Projects · GitHub

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
55
56
57
58
59
60
61
62
63
64
65
66
import streamlit as st
import speech_recognition as sr


class SpeechRecognitionApp:
    def __init__(self):
        self.recognizer = sr.Recognizer()
        self.microphone = sr.Microphone()
        self.transcribed_text = ""
        self.filename = ""
        self.language = ""

    def choose_api(self, api_choice):
        if api_choice == "Google Speech Recognition":
            self.recognizer_instance = sr.Recognizer()
        elif api_choice == "Microsoft Azure Speech":
            self.recognizer_instance = sr.Recognizer()
        elif api_choice == "Deepgram":
            self.recognizer_instance = sr.Recognizer()
        elif api_choice == "Speechbrain":
            self.recognizer_instance = sr.Recognizer()
        elif api_choice == "TorchAudio":
            self.recognizer_instance = sr.Recognizer()


    def transcribe_speech(self):
        with self.microphone as source:
            st.write("Speak something...")
            audio = self.recognizer.listen(source)

        try:
            self.transcribed_text = self.recognizer.recognize_google(audio)
        except sr.UnknownValueError:
            st.error("Sorry, could not understand audio.")
        except sr.RequestError as e:
            st.error(f"Request to API failed: {e}")

    def save_transcribed_text(self):
        if self.transcribed_text and self.filename:
            with open(self.filename, 'w') as file:
                file.write(self.transcribed_text)
            st.success(f"Transcribed text saved to {self.filename}")

    def choose_language(self):
        self.language = st.text_input("Enter the language code (e.g., en-US, fr-FR):")
        # Configure the recognizer to use the chosen language

    def run(self):
        st.title("Speech Recognition App 🌝")
        api_choice = st.selectbox("Select a speech recognition API:",
                                  ["Google Speech Recognition", "Microsoft Azure Speech", "Deepgram", "TorchAudio", "Speechbrain"])
        self.choose_api(api_choice)

        self.transcribe_speech()
        st.write("Transcribed Text:", self.transcribed_text)

        self.filename = st.text_input("Enter the filename to save the text:")
        self.save_transcribed_text()

        self.choose_language()
        st.button("Pause / Resume")  # Placeholder for pause/resume button


if __name__ == "__main__":
    app = SpeechRecognitionApp()
    app.run()