app.py

import gradio as gr
import torch
from transformers import pipeline
from timeit import default_timer as timer


username = "barto17"  ## Complete your username
model_id = f"{username}/distilhubert-finetuned-gtzan"
device = "cuda:0" if torch.cuda.is_available() else "cpu"
pipe = pipeline("audio-classification", model=model_id, device=device)

# def predict_trunc(filepath):
#     preprocessed = pipe.preprocess(filepath)
#     truncated = pipe.feature_extractor.pad(preprocessed,truncation=True, max_length = 16_000*30)
#     model_outputs = pipe.forward(truncated)
#     outputs = pipe.postprocess(model_outputs)

#     return outputs


def classify_audio(filepath):
    start_time = timer()
    """
      Goes from
      [{'score': 0.8339303731918335, 'label': 'country'},
    {'score': 0.11914275586605072, 'label': 'rock'},]
     to
     {"country":  0.8339303731918335, "rock":0.11914275586605072}
    """
    preds = pipe(filepath)
    # preds = predict_trunc(filepath)
    outputs = {}
    for p in preds:
        outputs[p["label"]] = p["score"]

    pred_time = round(timer() - start_time, 5)
    return outputs, pred_time


title = "🎵 Music Genre Classifier"
description = """
just demo
"""

filenames = ['sample_audio.mp3', 'sample_2.mp3', 'sample_3.mp3' ]
filenames = [[f"./{f}"] for f in filenames]
demo = gr.Interface(
    fn=classify_audio,
    inputs=gr.Audio(type="filepath"),
     outputs=[gr.Label(label="Predictions"), 
                             gr.Number(label="Prediction time (s)")],
    title=title,
    description=description,
    examples=filenames,
)
demo.launch()