File size: 1,911 Bytes
738671a
 
 
71422ef
738671a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71422ef
ee98ccd
738671a
 
71422ef
738671a
 
c38119e
 
738671a
 
c38119e
738671a
6140104
738671a
 
5474146
738671a
 
 
 
75a99cf
51bd00a
 
738671a
 
 
 
 
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
56
57
import gradio as gr
import torch
from transformers import pipeline
from timeit import default_timer as timer

username = "fmagot01"  ## 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):
    """
      Goes from
      [{'score': 0.8339303731918335, 'label': 'country'},
    {'score': 0.11914275586605072, 'label': 'rock'},]
     to
     {"country":  0.8339303731918335, "rock":0.11914275586605072}
    """
    start_time = timer()
    preds = pipe(filepath)
    # preds = predict_trunc(filepath)
    outputs = {}
    pred_time = round(timer() - start_time, 5)
    for p in preds:
        outputs[p["label"]] = p["score"]
    return outputs, pred_time
    #return outputs


title = "Classifier of Music Genres"
description = """
This is the demo of the finetuned classification model that we just trained on the [GTZAN](https://huggingface.co/datasets/marsyas/gtzan). You can upload your own audio file or used the ones already provided below.
"""

filenames = ['TAINY_88_melodic_loop_keys_las_Emin.wav', "TAINY_92_melodic_loop_keys_lam_Ebmin.wav", "TunePocket-Lively-Polka-Dance-30-Sec-Preview.mp3"]
filenames = [[f"./{f}"] for f in filenames]
demo = gr.Interface(
    fn=classify_audio,
    inputs=gr.Audio(type="filepath"),
    outputs=[gr.outputs.Label(label="Predictions"),
             gr.Number(label="Prediction time (s)")
            ],
    title=title,
    description=description,
    examples=filenames,
)
demo.launch()