app.py

import gradio as gr
from speechbrain.pretrained.interfaces import foreign_class



def main_note(filepath):
    classifier = foreign_class(source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP", pymodule_file="custom_interface.py", classname="CustomEncoderWav2vec2Classifier")
    # out_prob, score, index, text_lab = classifier.classify_file("speechbrain/emotion-recognition-wav2vec2-IEMOCAP/anger.wav")
    out_prob, score, index, text_lab = classifier.classify_file(filepath)
    return text_lab


demo = gr.Interface(
    fn= main_note,
    input = gr.Audio(type="filepath"),
    output= "text"
)

if __name__ == "__main__":
    demo.launch()