Update app.py

app.py

@@ -1,7 +1,62 @@
 import gradio as gr
+#import flask
+#from tkinter import filedialog
+import numpy as np
+import pandas as pd
+import csv
+import librosa
+import tensorflow as tf
 
-def greet(name):
-    return "Hello " + name + "!!"
+#!gdown https://drive.google.com/uc?id=1hKQdsTZ35KQmNV9Zrqg-ksTLSmPapR53
+model = tf.keras.models.load_model('TTM_model.h5')
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+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(audiox, temp):
+    audio=audiox.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).launch(debug=True)