Hugging Face's logo

Spaces:
Redmind
/
Audio_transcription
Sleeping

App Files Community
Audio_transcription
File size: 4,909 Bytes 
221417c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
452575b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
221417c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
 
import gradio as gr
import openai
import deepgram_sdk
import assemblyai
from transformers import pipeline

# Initialize sentiment analysis model
sentiment_analyzer = pipeline("text-classification", model="Vasanth/tamil-sentiment-distilbert")

# Placeholder transcription functions - Replace with your actual API implementation
def whisper_openai_transcribe(audio_file):
    # Replace with actual Whisper API transcription code
    transcription = "This is a dummy transcription from Whisper OpenAI API"
    return transcription

def deepgram_transcribe(audio_file):
    # Replace with actual Deepgram API transcription code
    transcription = "This is a dummy transcription from Deepgram API"
    return transcription

def assemblyai_transcribe(audio_file):
    import assemblyai as aai

    # Replace with your API key
    aai.settings.api_key = "96206c6070cf4157b84f4f8eb66b5903"
    
    # URL of the file to transcribe
    #FILE_URL = "https://assemblyaiusercontent.com/playground/ECw2Ncu7btO.mp3"
    #FILE_URL = "C:/lakshmi/AI usecases/tamil_audio1.mp3"
    
    # You can also transcribe a local file by passing in a file path
    # FILE_URL = './path/to/file.mp3'
    
    # You can set additional parameters for the transcription
    config = aai.TranscriptionConfig(
      speech_model=aai.SpeechModel.nano,
      
      language_detection=True
    )
    
    transcriber = aai.Transcriber(config=config)
    transcript = transcriber.transcribe(audio_file)
    
    if transcript.status == aai.TranscriptStatus.error:
        print(transcript.error)
    else:
        print(transcript.text)
    # Load a pre-trained sentiment analysis model for Tamil
    #test_script = "இந்த செய்தி மிகவும் சோகம் மிகுந்தது.இந்த செய்தி நன்றாக உள்ளது."
    """from transformers import pipeline
    sentiment_analyzer = pipeline("sentiment-analysis", model="nlptown/bert-base-multilingual-uncased-sentiment")
    result = sentiment_analyzer(transcript.text)
    print(result)
    
    lines = test_script.split('.')  # Split the transcript into lines
    sentiment_results = []
    
    for line in lines:
        line = line.strip()  # Remove leading/trailing whitespace
        if line:  # Only analyze non-empty lines
            sentiment = sentiment_analyzer(line)
            sentiment_results.append((line, sentiment))
    print(sentiment_results)
    # Write the Tamil text to a file
    with open("tamil_text1.txt", "w", encoding="utf-8") as file:
        file.write(transcript.text)
    
    # Write the sentiment analysis results to a file 
    
    # Write the list of dictionaries in a human-readable format
    with open("tamil_result.txt", 'w', encoding='utf-8') as file:
        for result in sentiment_results:
            file.write(f"Label: {result[0]}, Score: {result[1]}\n")
    """
    return transcription

# Sentiment analysis function
def analyze_sentiment(text):
    sentiment = sentiment_analyzer(text)
    return sentiment[0]['label'], sentiment[0]['score']

# Main function to process audio and sentiment analysis
def process_transcription_and_sentiment(audio_file, model_choice):
    # Transcription
    if model_choice == "Whisper OpenAI":
        transcription = whisper_openai_transcribe(audio_file)
    elif model_choice == "Deepgram API":
        transcription = deepgram_transcribe(audio_file)
    elif model_choice == "Assembly AI API":
        transcription = assemblyai_transcribe(audio_file)
    
    # Sentiment analysis
    sentiment_label, sentiment_score = analyze_sentiment(transcription)
    
    return transcription, f"Sentiment: {sentiment_label} with score {sentiment_score}"

# Gradio interface setup
def create_interface():
    with gr.Blocks() as demo:
        gr.Markdown("### Audio Transcription and Sentiment Analysis")
        
        with gr.Row():
            audio_input = gr.Audio(source="upload", type="file", label="Upload Audio File")
            model_choice = gr.Dropdown(
                choices=["Whisper OpenAI", "Deepgram API", "Assembly AI API"],
                label="Choose Transcription Model",
                value="Whisper OpenAI"
            )
        
        # Textboxes for transcription and sentiment analysis
        transcription_output = gr.Textbox(label="Transcription", lines=5)
        sentiment_output = gr.Textbox(label="Sentiment Analysis", lines=5)
        
        # Submit button
        submit_button = gr.Button("Process")
        
        # When the button is clicked, call the `process_transcription_and_sentiment` function
        submit_button.click(process_transcription_and_sentiment, 
                            inputs=[audio_input, model_choice], 
                            outputs=[transcription_output, sentiment_output])
        
    demo.launch()

if __name__ == "__main__":
    create_interface()