app.py

import gradio as gr
import torch
import whisper
from transformers import pipeline

### ————————————————————————————————————————

title="Whisper to Emotion"

### ————————————————————————————————————————

whisper_model = whisper.load_model("small")

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

emotion_classifier = pipeline("text-classification",model='bhadresh-savani/distilbert-base-uncased-emotion')

def translate_and_classify(audio):
    
    print("""
    —
    Sending audio to Whisper ...
    —
    """)
    audio = whisper.load_audio(audio)
    audio = whisper.pad_or_trim(audio)
    
    mel = whisper.log_mel_spectrogram(audio).to(whisper_model.device)
    
    _, probs = whisper_model.detect_language(mel)
    
    transcript_options = whisper.DecodingOptions(task="transcribe", fp16 = False)
    translate_options = whisper.DecodingOptions(task="translate", fp16 = False)
    
    transcription = whisper.decode(whisper_model, mel, transcript_options)
    translation = whisper.decode(whisper_model, mel, translate_options)
    
    print("Language Spoken: " + transcription.language)
    print("Transcript: " + transcription.text)  
    print("Translated: " + translation.text)
    
    emotion = emotion_classifier(translation.text)
    detected_emotion = emotion[0]["label"]
    print("Detected Emotions are", detected_emotion)
    return transcription.text, detected_emotion

css = """
        .gradio-container {
            font-family: 'IBM Plex Sans', sans-serif;
        }
        .gr-button {
            color: white;
            border-color: black;
            background: black;
        }
        input[type='range'] {
            accent-color: black;
        }
        .dark input[type='range'] {
            accent-color: #dfdfdf;
        }
        .container {
            max-width: 730px;
            margin: auto;
            padding-top: 1.5rem;
        }
        #gallery {
            min-height: 22rem;
            margin-bottom: 15px;
            margin-left: auto;
            margin-right: auto;
            border-bottom-right-radius: .5rem !important;
            border-bottom-left-radius: .5rem !important;
        }
        #gallery>div>.h-full {
            min-height: 20rem;
        }
        .details:hover {
            text-decoration: underline;
        }
        .gr-button {
            white-space: nowrap;
        }
        .gr-button:focus {
            border-color: rgb(147 197 253 / var(--tw-border-opacity));
            outline: none;
            box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
            --tw-border-opacity: 1;
            --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
            --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
            --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
            --tw-ring-opacity: .5;
        }
        #advanced-btn {
            font-size: .7rem !important;
            line-height: 19px;
            margin-top: 12px;
            margin-bottom: 12px;
            padding: 2px 8px;
            border-radius: 14px !important;
        }
        #advanced-options {
            display: none;
            margin-bottom: 20px;
        }
        .footer {
            margin-bottom: 45px;
            margin-top: 35px;
            text-align: center;
            border-bottom: 1px solid #e5e5e5;
        }
        .footer>p {
            font-size: .8rem;
            display: inline-block;
            padding: 0 10px;
            transform: translateY(10px);
            background: white;
        }
        .dark .footer {
            border-color: #303030;
        }
        .dark .footer>p {
            background: #0b0f19;
        }


"""
with gr.Blocks(css = css) as demo:
    gr.Markdown("""
                ## Emotion Detection From Speech with Whisper
            """)
    gr.HTML('''
     <p style="margin-bottom: 10px; font-size: 94%">
                Whisper is a general-purpose speech recognition model released by OpenAI that can perform multilingual speech recognition as well as speech translation and language identification. This allows for detecting emotion directly from speech in multiple languages 
              </p>
              ''')
    
    with gr.Column():
            #gr.Markdown(""" ### Record audio """)
        with gr.Tab("Record Audio"):
            audio_input_r = gr.Audio(label = 'Record Audio Input',source="microphone",type="filepath")
            transcribe_audio_r = gr.Button('Transcribe')
        
        with gr.Tab("Upload Audio as File"):
            audio_input_u = gr.Audio(label = 'Upload Audio',source="upload",type="filepath")
            transcribe_audio_u = gr.Button('Transcribe')

        with gr.Row():
            transcript_output = gr.Textbox(label="Transcription in the language you spoke", lines = 3)
            emotion_output = gr.Textbox(label = "Detected Emotion")
    
    transcribe_audio_r.click(translate_and_classify, inputs = audio_input_r, outputs = [transcript_output,emotion_output])
    transcribe_audio_u.click(translate_and_classify, inputs = audio_input_u, outputs = [transcript_output,emotion_output])    
    gr.HTML('''
        <div class="footer">
                    <p>Whisper Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a> -   
                    <a href="https://huggingface.co/bhadresh-savani/distilbert-base-uncased-emotion" style="text-decoration: underline;" target="_blank">Emotion Detection Model</a>
                    </p>
        </div>
        ''')
    
    
demo.launch()