Upload 5 files

app.py

@@ -0,0 +1,86 @@
+import gradio as gr
+from keras.models import model_from_json
+import matplotlib.pyplot as plt
+import keras 
+import pickle
+import pandas as pd
+import numpy as np
+import librosa
+import librosa.display
+
+def transform_data(audio):
+    print("audio: ", audio)
+    # Lets transform the dataset so we can apply the predictions
+    X, sample_rate = librosa.load(audio
+                                ,res_type='kaiser_fast'
+                                ,duration=2.5
+                                ,sr=44100
+                                ,offset=0.5
+                                )
+    
+    print("HEREEEE", sample_rate, X.shape)
+
+    sample_rate = np.array(sample_rate)
+    mfccs = np.mean(librosa.feature.mfcc(y=X, sr=sample_rate, n_mfcc=13),axis=0)
+    newdf = pd.DataFrame(data=mfccs).T
+    return newdf
+
+def predict(newdf, loaded_model):
+    # Apply predictions
+    newdf= np.expand_dims(newdf, axis=2)
+    print("***HERRRREEEEE*** ", newdf.shape )
+    newpred = loaded_model.predict(newdf, 
+                            batch_size=16, 
+                            verbose=1)
+    return newpred
+
+    
+def get_label(newpred):
+    filename = 'models/labels'
+    infile = open(filename,'rb')
+    lb = pickle.load(infile)
+    infile.close()
+
+    # Get the final predicted label
+    final = newpred.argmax(axis=1)
+    final = final.astype(int).flatten()
+    final = (lb.inverse_transform((final)))
+    return final
+
+def load_model():
+    # loading json and model architecture 
+    json_file = open('models/model_json.json', 'r')
+    loaded_model_json = json_file.read()
+    json_file.close()
+    loaded_model = model_from_json(loaded_model_json)
+
+    # load weights into new model
+    loaded_model.load_weights("models/Emotion_Model.h5")
+    print("Loaded model from disk")
+
+    # the optimiser
+    opt = keras.optimizers.RMSprop(lr=0.00001, decay=1e-6)
+    loaded_model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
+    return loaded_model
+
+
+def main(audio):
+    newdf = transform_data(audio)
+    loaded_model = load_model()
+    newpred = predict(newdf, loaded_model)
+    final = get_label(newpred)
+    return "Classification: " + final
+
+demo = gr.Interface(
+    main,
+    inputs=gr.Audio(
+        sources=["microphone"],
+        type="filepath",
+    ), 
+    outputs="text"
+    )
+    
+
+
+if __name__ == "__main__":
+    demo.launch(show_api=False) 

models/Emotion_Model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baba567dca858b61c748bd2b8d6baaaeb818fc72e627d2e5cd4eb0496b7714a7
+size 10391096

models/model_json.json

@@ -0,0 +1 @@
+{"class_name": "Sequential", "config": {"name": "sequential", "layers": [{"class_name": "InputLayer", "config": {"batch_input_shape": [null, 216, 1], "dtype": "float32", "sparse": false, "ragged": false, "name": "conv1d_input"}}, {"class_name": "Conv1D", "config": {"name": "conv1d", "trainable": true, "batch_input_shape": [null, 216, 1], "dtype": "float32", "filters": 256, "kernel_size": [8], "strides": [1], "padding": "same", "data_format": "channels_last", "dilation_rate": [1], "groups": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Activation", "config": {"name": "activation", "trainable": true, "dtype": "float32", "activation": "relu"}}, {"class_name": "Conv1D", "config": {"name": "conv1d_1", "trainable": true, "dtype": "float32", "filters": 256, "kernel_size": [8], "strides": [1], "padding": "same", "data_format": "channels_last", "dilation_rate": [1], "groups": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "BatchNormalization", "config": {"name": "batch_normalization", "trainable": true, "dtype": "float32", "axis": [2], "momentum": 0.99, "epsilon": 0.001, "center": true, "scale": true, "beta_initializer": {"class_name": "Zeros", "config": {}}, "gamma_initializer": {"class_name": "Ones", "config": {}}, "moving_mean_initializer": {"class_name": "Zeros", "config": {}}, "moving_variance_initializer": {"class_name": "Ones", "config": {}}, "beta_regularizer": null, "gamma_regularizer": null, "beta_constraint": null, "gamma_constraint": null}}, {"class_name": "Activation", "config": {"name": "activation_1", "trainable": true, "dtype": "float32", "activation": "relu"}}, {"class_name": "Dropout", "config": {"name": "dropout", "trainable": true, "dtype": "float32", "rate": 0.25, "noise_shape": null, "seed": null}}, {"class_name": "MaxPooling1D", "config": {"name": "max_pooling1d", "trainable": true, "dtype": "float32", "strides": [8], "pool_size": [8], "padding": "valid", "data_format": "channels_last"}}, {"class_name": "Conv1D", "config": {"name": "conv1d_2", "trainable": true, "dtype": "float32", "filters": 128, "kernel_size": [8], "strides": [1], "padding": "same", "data_format": "channels_last", "dilation_rate": [1], "groups": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Activation", "config": {"name": "activation_2", "trainable": true, "dtype": "float32", "activation": "relu"}}, {"class_name": "Conv1D", "config": {"name": "conv1d_3", "trainable": true, "dtype": "float32", "filters": 128, "kernel_size": [8], "strides": [1], "padding": "same", "data_format": "channels_last", "dilation_rate": [1], "groups": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Activation", "config": {"name": "activation_3", "trainable": true, "dtype": "float32", "activation": "relu"}}, {"class_name": "Conv1D", "config": {"name": "conv1d_4", "trainable": true, "dtype": "float32", "filters": 128, "kernel_size": [8], "strides": [1], "padding": "same", "data_format": "channels_last", "dilation_rate": [1], "groups": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Activation", "config": {"name": "activation_4", "trainable": true, "dtype": "float32", "activation": "relu"}}, {"class_name": "Conv1D", "config": {"name": "conv1d_5", "trainable": true, "dtype": "float32", "filters": 128, "kernel_size": [8], "strides": [1], "padding": "same", "data_format": "channels_last", "dilation_rate": [1], "groups": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "BatchNormalization", "config": {"name": "batch_normalization_1", "trainable": true, "dtype": "float32", "axis": [2], "momentum": 0.99, "epsilon": 0.001, "center": true, "scale": true, "beta_initializer": {"class_name": "Zeros", "config": {}}, "gamma_initializer": {"class_name": "Ones", "config": {}}, "moving_mean_initializer": {"class_name": "Zeros", "config": {}}, "moving_variance_initializer": {"class_name": "Ones", "config": {}}, "beta_regularizer": null, "gamma_regularizer": null, "beta_constraint": null, "gamma_constraint": null}}, {"class_name": "Activation", "config": {"name": "activation_5", "trainable": true, "dtype": "float32", "activation": "relu"}}, {"class_name": "Dropout", "config": {"name": "dropout_1", "trainable": true, "dtype": "float32", "rate": 0.25, "noise_shape": null, "seed": null}}, {"class_name": "MaxPooling1D", "config": {"name": "max_pooling1d_1", "trainable": true, "dtype": "float32", "strides": [8], "pool_size": [8], "padding": "valid", "data_format": "channels_last"}}, {"class_name": "Conv1D", "config": {"name": "conv1d_6", "trainable": true, "dtype": "float32", "filters": 64, "kernel_size": [8], "strides": [1], "padding": "same", "data_format": "channels_last", "dilation_rate": [1], "groups": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Activation", "config": {"name": "activation_6", "trainable": true, "dtype": "float32", "activation": "relu"}}, {"class_name": "Conv1D", "config": {"name": "conv1d_7", "trainable": true, "dtype": "float32", "filters": 64, "kernel_size": [8], "strides": [1], "padding": "same", "data_format": "channels_last", "dilation_rate": [1], "groups": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Activation", "config": {"name": "activation_7", "trainable": true, "dtype": "float32", "activation": "relu"}}, {"class_name": "Flatten", "config": {"name": "flatten", "trainable": true, "dtype": "float32", "data_format": "channels_last"}}, {"class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": "float32", "units": 14, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Activation", "config": {"name": "activation_8", "trainable": true, "dtype": "float32", "activation": "softmax"}}]}, "keras_version": "2.10.0", "backend": "tensorflow"}