Skip to content

2
2021-060
Commit 92e7ac9b authored by Dhananjaya Jayashanka's avatar Dhananjaya Jayashanka
Browse files
Options

update IT18126884 branch

parent a5871b71
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 281 deletions
Filler Words/FillerAPI.py deleted 100644 → 0
View file @ a5871b71
import flask
from flask_cors import CORS, cross_origin
import getFillterWordCount
app = flask.Flask(__name__)
cors = CORS(app)
app.config['CORS_HEADERS'] = 'Content-Type'
app.config["DEBUG"] = True
@app.route('/countFillerWords', methods=['GET'])
@cross_origin()
def countFillerWords():
fillterWordCount = getFillterWordCount.countFillerWords("../temp.wav")
return fillterWordCount
app.run(port=5001)
Filler Words/Train_Neural_Network.py deleted 100644 → 0
View file @ a5871b71
import numpy as np
import scikitplot
from sklearn.metrics import classification_report
from sklearn.preprocessing import LabelEncoder
from keras.utils import to_categorical
from sklearn.model_selection import train_test_split
import get_features
import neural_network
from matplotlib import pyplot
import sys
def get_numpy_array(features_df):
X = np.array(features_df.feature.tolist())
y = np.array(features_df.class_label.tolist())
# encode classification labels
le = LabelEncoder()
# one hot encoded labels
yy = to_categorical(le.fit_transform(y))
return X, yy, le
def get_train_test(X, y):
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
return X_train, X_test, y_train, y_test
if __name__ == "__main__":
# extract features
print("Extracting features..")
features_df = get_features.extract_features()
# convert into numpy array
X, y, le = get_numpy_array(features_df)
# split into training and testing data
X_train, X_test, y_train, y_test = get_train_test(X, y)
num_labels = y.shape[1]
X_train = np.expand_dims(X_train, axis=2)
X_test = np.expand_dims(X_test, axis=2)
# create model architecture
model = neural_network.create_cnn(num_labels)
# train model
print("Training..")
neural_network.train(model, X_train, X_test, y_train, y_test, "trained_cnn.h5")
# compute test loss and accuracy
test_loss, test_accuracy = neural_network.compute(X_test, y_test, "trained_cnn.h5")
print("Test loss", test_loss)
print("Test accuracy", test_accuracy)
# predicting using trained model with any test file in dataset
neural_network.predict("data/ab/ab.ogg", le, "trained_cnn.h5")
yhat_valid = model.predict_classes(X_train)
scikitplot.metrics.plot_confusion_matrix(np.argmax(y_train, axis=1), yhat_valid, figsize=(7, 7))
pyplot.savefig("confusion_matrix_dcnn.png")
print(f'total wrong validation predictions: {np.sum(np.argmax(y_train, axis=1) != yhat_valid)}\n\n')
print(classification_report(np.argmax(y_train, axis=1), yhat_valid))
Filler Words/getFillterWordCount.py deleted 100644 → 0
View file @ a5871b71
import os
from pydub import AudioSegment
from pydub.silence import split_on_silence
from tensorflow.keras.utils import to_categorical
from sklearn.preprocessing import LabelEncoder
import numpy as np
import get_features
import neural_network
# countPauses("../content analyzing/temp.wav")
ScoreforUserSilence = 70/100
def get_numpy_array(features_df):
X = np.array(features_df.feature.tolist())
y = np.array(features_df.class_label.tolist())
# encode classification labels
le = LabelEncoder()
# one hot encoded labels
yy = to_categorical(le.fit_transform(y))
return X, yy, le
features_df = get_features.extract_features()
X, y, le = get_numpy_array(features_df)
def countFillerWords(filePath):
fillerWordCount = 0
sound = AudioSegment.from_wav(filePath)
chunks = split_on_silence(sound, min_silence_len=200, silence_thresh=sound.dBFS - 16, keep_silence=150)
# Chunk Folder file Path
chunk_folder_name = "chunks"
# create folder to store chunks
if not os.path.isdir(chunk_folder_name):
os.mkdir(chunk_folder_name)
for i, audio_chunk in enumerate(chunks, start=1):
chunk_file = os.path.join(chunk_folder_name, f"chunk{i}.wav")
audio_chunk.export(chunk_file, format="wav", bitrate='192k')
prediction = neural_network.predict(chunk_file, le, "trained_cnn.h5")
print(prediction)
if float(prediction["probability"]) > 0.99:
fillerWordCount += 1
print("****** How many times Filler words in their Speech *****")
# print count of silence
print("Filler words: ", fillerWordCount)
return {
"message": str(fillerWordCount) + " : filler word/s found",
"score": ScoreforUserSilence
}
# countFillerWords("../audio.wav")
Filler Words/get_features.py deleted 100644 → 0
View file @ a5871b71
import os
import librosa
import soundfile as sf
import numpy as np
import glob
import pandas as pd
def get_features(file_name):
print(sf.available_formats())
if file_name:
X, sample_rate = sf.read(file_name, dtype='float32')
# mfcc (mel-frequency cepstrum)
print("sample rate: ", sample_rate)
monoX = []
for leftX in X:
if len(X.shape) == 2:
monoX.append(leftX[0])
else:
monoX.append(leftX)
shape = np.shape(monoX)
padded_array = np.zeros((300000))
print(len(monoX))
if len(monoX) > 300000:
return []
padded_array[:shape[0]] = monoX
mfccs = librosa.feature.mfcc(y=padded_array, sr=sample_rate, n_mfcc=40)
mfccs_scaled = np.mean(mfccs.T,axis=0)
return mfccs_scaled
def extract_features():
# path to dataset containing 10 subdirectories of .ogg files
sub_dirs = os.listdir('/data')
sub_dirs.sort()
print(sub_dirs)
features_list = []
for label, sub_dir in enumerate(sub_dirs):
for file_name in glob.glob(os.path.join('data',sub_dir,"*.ogg")):
print("Extracting file ", file_name)
try:
mfccs = get_features(file_name)
except Exception as e:
print(e)
print("Extraction error")
continue
features_list.append([mfccs,label])
features_df = pd.DataFrame(features_list,columns = ['feature','class_label'])
print(features_df.head())
return features_df
Filler Words/neural_network.py deleted 100644 → 0
View file @ a5871b71
# Imports
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv1D, GlobalAveragePooling1D, MaxPooling1D
from keras.models import load_model
import get_features
from sklearn.preprocessing import LabelEncoder
import numpy as np
import os
def create_mlp(num_labels):
model = Sequential()
model.add(Dense(256,input_shape = (40,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(256,input_shape = (40,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_labels))
model.add(Activation('softmax'))
return model
def create_cnn(num_labels):
model = Sequential()
model.add(Conv1D(64, 3, activation='relu', input_shape=(40, 1)))
model.add(Conv1D(64, 3, activation='relu'))
model.add(MaxPooling1D(3))
model.add(Conv1D(128, 3, activation='relu'))
model.add(Conv1D(128, 3, activation='relu'))
model.add(GlobalAveragePooling1D())
model.add(Dropout(0.5))
model.add(Dense(num_labels))
model.add(Activation('softmax'))
return model
def train(model,X_train, X_test, y_train, y_test,model_file):
# compile the model
model.compile(loss = 'categorical_crossentropy',metrics=['accuracy'],optimizer='adam')
print(model.summary())
print("training for 100 epochs with batch size 32")
model.fit(X_train,y_train,batch_size= 10, epochs = 100, validation_data=(X_test,y_test))
# save model to disk
print("Saving model to disk")
model.save(model_file)
def compute(X_test,y_test,model_file):
# load model from disk
loaded_model = load_model(model_file)
score = loaded_model.evaluate(X_test,y_test)
return score[0],score[1]*100
def predict(filename,le,model_file):
model = load_model(model_file)
prediction_feature = get_features.get_features(filename)
if len(prediction_feature) == 0:
return {"pred": "", "probability": str(0)}
if model_file == "trained_mlp.h5":
prediction_feature = np.array([prediction_feature])
elif model_file == "trained_cnn.h5":
prediction_feature = np.expand_dims(np.array([prediction_feature]),axis=2)
predicted_vector = model.predict_classes(prediction_feature)
predicted_class = le.inverse_transform(predicted_vector)
sub_dirs = os.listdir('data')
sub_dirs.sort()
print("Predicted class",sub_dirs[predicted_class[0]])
predicted_proba_vector = model.predict_proba([prediction_feature])
word = ""
probability = 0
predicted_proba = predicted_proba_vector[0]
for i in range(len(predicted_proba)):
category = le.inverse_transform(np.array([i]))
print(category[0], "\t\t : ", format(predicted_proba[i], '.32f') )
if (predicted_proba[i] > probability):
probability = predicted_proba[i]
word = sub_dirs[predicted_class[0]]
print("Selected word: ", word)
return {"pred": word, "probability": str(probability)}
Flow of the sppech/README.md deleted 100644 → 0
View file @ a5871b71
read me
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment