Spaces:
Runtime error
Runtime error
File size: 2,286 Bytes
d3d38a1 94c1c1f d3d38a1 94c1c1f d3d38a1 94c1c1f 4749619 94c1c1f 46cf0b4 |
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 58 59 60 61 62 63 |
import gradio as gr
import numpy as np
import pandas as pd
import csv
import librosa
import tensorflow as tf
#!gdown https://drive.google.com/uc?id=1hKQdsTZ35KQmNV9Zrqg-ksTLSmPapR53
model = tf.keras.models.load_model('TTM_model.h5')
def config_audio(audio):
print('enter2')
header = 'ChromaSTFT RMS SpectralCentroid SpectralBandwidth Rolloff ZeroCrossingRate'
for i in range(1, 21):
header += f' mfcc{i}'
header += ' label'
header = header.split()
print(1)
file = open('predict_file.csv', 'w', newline='')
with file:
writer = csv.writer(file)
writer.writerow(header)
print(2)
#taalfile = audio
#print('stored in taalfile')
y, sr = librosa.load(audio, mono=True, duration=30)
print(3)
rms = librosa.feature.rms(y=y)
chroma = librosa.feature.chroma_stft(y=y, sr=sr)
spec_centroid = librosa.feature.spectral_centroid(y=y, sr=sr)
spec_bandwidth = librosa.feature.spectral_bandwidth(y=y, sr=sr)
rolloff = librosa.feature.spectral_rolloff(y=y, sr=sr)
zcr = librosa.feature.zero_crossing_rate(y)
mfcc = librosa.feature.mfcc(y=y, sr=sr)
to_append = f' {np.mean(chroma)} {np.mean(rms)} {np.mean(spec_centroid)} {np.mean(spec_bandwidth)} {np.mean(rolloff)} {np.mean(zcr)} '
for e in mfcc:
to_append += f' {np.mean(e)}'
#to_append += f' {t}'
file = open('predict_file.csv', 'a', newline='')
with file:
writer = csv.writer(file)
writer.writerow(to_append.split())
predict_file = pd.read_csv("predict_file.csv")
X_predict = predict_file.drop('label', axis=1)
print('exit2')
return X_predict
def predict_audio(Input_Audio, Playable_Audio):
audio=Input_Audio.name
print('enter1')
X_predict = config_audio(audio)
taals = ['addhatrital','bhajani','dadra','deepchandi','ektal','jhaptal','rupak','trital']
pred = model.predict(X_predict).flatten()
print('exit1')
return {taals[i]: float(pred[i]) for i in range(7)}
audio = gr.inputs.Audio(source="upload", optional=False)
label = gr.outputs.Label()
gr.Interface(predict_audio,
["file","audio"],
outputs=label,
description="").launch(debug=True) |