from transformers import pipeline, Wav2Vec2Processor, Wav2Vec2ForSequenceClassification
import gradio as gr

model_id = "Tirath5504/distilhubert-finetuned-gtzan"
processor = Wav2Vec2Processor.from_pretrained(model_id)
model = Wav2Vec2ForSequenceClassification.from_pretrained(model_id)
pipe = pipeline("audio-classification", model=model, processor=processor)

def classify_audio(filepath):
    preds = pipe(filepath)
    outputs = {}
    for p in preds:
        outputs[p["label"]] = p["score"]
    return outputs

demo = gr.Interface(
    fn=classify_audio, inputs=gr.Audio(type="filepath"), outputs=gr.outputs.Label()
)
demo.launch(debug=True)