Update app.py
Browse files
app.py
CHANGED
@@ -5,16 +5,20 @@ import numpy as np
|
|
5 |
import matplotlib.pyplot as plt
|
6 |
from pydub import AudioSegment
|
7 |
import tempfile
|
|
|
8 |
|
9 |
learn = load_learner('model.pkl')
|
10 |
labels = learn.dls.vocab
|
11 |
|
12 |
def audio_to_spectrogram(audio_file):
|
13 |
-
if audio_file
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
|
|
|
|
|
|
18 |
else:
|
19 |
y, sr = librosa.load(audio_file, sr=None)
|
20 |
|
@@ -36,11 +40,11 @@ def predict(audio):
|
|
36 |
pred, pred_idx, probs = learn.predict(img)
|
37 |
return {labels[i]: float(probs[i]) for i in range(len(labels))}
|
38 |
|
39 |
-
examples = ['example_audio.mp3']
|
40 |
-
|
41 |
gr.Interface(
|
42 |
fn=predict,
|
43 |
-
inputs=
|
|
|
|
|
44 |
outputs=gr.components.Label(num_top_classes=3),
|
45 |
-
|
46 |
-
).launch()
|
|
|
5 |
import matplotlib.pyplot as plt
|
6 |
from pydub import AudioSegment
|
7 |
import tempfile
|
8 |
+
import PIL
|
9 |
|
10 |
learn = load_learner('model.pkl')
|
11 |
labels = learn.dls.vocab
|
12 |
|
13 |
def audio_to_spectrogram(audio_file):
|
14 |
+
if isinstance(audio_file, str):
|
15 |
+
if audio_file.endswith('.mp3'):
|
16 |
+
with tempfile.NamedTemporaryFile(suffix='.wav') as temp_wav:
|
17 |
+
audio = AudioSegment.from_mp3(audio_file)
|
18 |
+
audio.export(temp_wav.name, format='wav')
|
19 |
+
y, sr = librosa.load(temp_wav.name, sr=None)
|
20 |
+
else:
|
21 |
+
y, sr = librosa.load(audio_file, sr=None)
|
22 |
else:
|
23 |
y, sr = librosa.load(audio_file, sr=None)
|
24 |
|
|
|
40 |
pred, pred_idx, probs = learn.predict(img)
|
41 |
return {labels[i]: float(probs[i]) for i in range(len(labels))}
|
42 |
|
|
|
|
|
43 |
gr.Interface(
|
44 |
fn=predict,
|
45 |
+
inputs=[
|
46 |
+
gr.Audio(sources=["upload", "microphone"], type="filepath", label="Upload or Record audio (WAV or MP3)"),
|
47 |
+
],
|
48 |
outputs=gr.components.Label(num_top_classes=3),
|
49 |
+
live=True
|
50 |
+
).launch()
|