app.py

import gradio as gr
import torch
import whisper

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

title="Whisper to Emotion"

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

whisper_model = whisper.load_model("small")

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

def translate(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)
        
    return transcription.text

with gr.Blocks() as demo:
    gr.Markdown("""
                # Emotion Detection From Speech Using Whisper
    
            """)
    audio_input = gr.Audio(label = 'Record Audio Input',source="microphone",type="filepath")
    
    transcript_output = gr.Textbox(label="Transcription in your the language you spoke")
    
    iface = gr.Interface(fn=translate, inputs=audio_input, outputs=transcript_output)
demo.launch()