Spaces:
Sleeping
Sleeping
File size: 1,519 Bytes
4862fc7 96fc794 4862fc7 96fc794 4862fc7 96fc794 4862fc7 e7b15aa 4862fc7 23a184a 4862fc7 23a184a 96fc794 e7b15aa 4862fc7 e7b15aa 4862fc7 96fc794 4862fc7 23a184a 96fc794 4862fc7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
import gradio as gr
import torch
from transformers import pipeline
username = "ardneebwar" ## 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):
import time
start_time = time.time()
# Assuming `pipe` is your model pipeline for inference
preds = pipe(filepath)
outputs = {}
for p in preds:
outputs[p["label"]] = p["score"]
end_time = time.time()
prediction_time = end_time - start_time
return outputs, prediction_time
title = "🎵 Music Genre Classifier"
description = """
Music Genre Classifier model (Fine-tuned "ntu-spml/distilhubert") Dataset: [GTZAN](https://huggingface.co/datasets/marsyas/gtzan)
"""
filenames = ['rock-it-21275.mp3']
filenames = [f"./{f}" for f in filenames]
demo = gr.Interface(
fn=classify_audio,
inputs=gr.Audio(type="filepath"),
outputs=[gr.Label(), gr.Number(label="Prediction time (s)")], # Using updated component names
title=title,
description=description,
examples=[(f,) for f in filenames],
)
demo.launch()
|