Skip to content

Inconsistent use of tabs and spaces #26

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Inconsistent use of tabs and spaces #26

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
202 changes: 101 additions & 101 deletions myprosody.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,21 +308,21 @@ def myprosody(m,p):
np.savetxt(outo,result_array, fmt='%s',delimiter=',')
#Data and features analysis
df = pd.read_csv(outo,
names = ['avepauseduratin','avelongpause','speakingtot','avenumberofwords','articulationrate','inpro','f1norm','mr','q25',
'q50','q75','std','fmax','fmin','vowelinx1','vowelinx2','formantmean','formantstd','nuofwrds','npause','ins',
'fillerratio','xx','xxx','totsco','xxban','speakingrate'],na_values='?')
names = ['avepauseduratin','avelongpause','speakingtot','avenumberofwords','articulationrate','inpro','f1norm','mr','q25',
'q50','q75','std','fmax','fmin','vowelinx1','vowelinx2','formantmean','formantstd','nuofwrds','npause','ins',
'fillerratio','xx','xxx','totsco','xxban','speakingrate'],na_values='?')
scoreMLdataset=df.drop(['xxx','xxban'], axis=1)
scoreMLdataset.to_csv(outst, header=False,index = False)
newMLdataset=df.drop(['avenumberofwords','f1norm','inpro','q25','q75','vowelinx1','nuofwrds','npause','xx','totsco','xxban','speakingrate','fillerratio'], axis=1)
newMLdataset.to_csv(outsy, header=False,index = False)
namess=nms = ['avepauseduratin','avelongpause','speakingtot','articulationrate','mr',
'q50','std','fmax','fmin','vowelinx2','formantmean','formantstd','ins',
'xxx']
'q50','std','fmax','fmin','vowelinx2','formantmean','formantstd','ins',
'xxx']
df1 = pd.read_csv(outsy, names = namess)
nsns=['average_syll_pause_duration','No._long_pause','speaking_time','ave_No._of_words_in_minutes','articulation_rate','No._words_in_minutes','formants_index','f0_index','f0_quantile_25_index',
'f0_quantile_50_index','f0_quantile_75_index','f0_std','f0_max','f0_min','No._detected_vowel','perc%._correct_vowel','(f2/f1)_mean','(f2/f1)_std',
'no._of_words','no._of_pauses','intonation_index',
'(voiced_syll_count)/(no_of_pause)','TOEFL_Scale_Score','Score_Shannon_index','speaking_rate']
'f0_quantile_50_index','f0_quantile_75_index','f0_std','f0_max','f0_min','No._detected_vowel','perc%._correct_vowel','(f2/f1)_mean','(f2/f1)_std',
'no._of_words','no._of_pauses','intonation_index',
'(voiced_syll_count)/(no_of_pause)','TOEFL_Scale_Score','Score_Shannon_index','speaking_rate']
dataframe = pd.read_csv(pa2)
df55 = pd.read_csv(outst,names=nsns)
dataframe=dataframe.values
Expand All @@ -343,109 +343,109 @@ def myprosody(m,p):
dfout = "%s:\t (%s)" % (nsns[i],":Out of Range")
print(dfout)
except:
print ("Try again the sound of the audio was not clear")
print ("Try again the sound of the audio was not clear")

def mysplev(m,p):
"""
Spoken Language Proficiency Level estimator,
based on Machine Learning models of the prosodic features of your speech
"""
import sys
def my_except_hook(exctype, value, traceback):
print('There has been an error in the system')
sys.excepthook = my_except_hook
import warnings
if not sys.warnoptions:
warnings.simplefilter("ignore")
sound=p+"/"+"dataset"+"/"+"audioFiles"+"/"+m+".wav"
sourcerun=p+"/"+"dataset"+"/"+"essen"+"/"+"MLTRNL.praat"
path=p+"/"+"dataset"+"/"+"audioFiles"+"/"
pa1=p+"/"+"dataset"+"/"+"datanewchi23.csv"
pa7=p+"/"+"dataset"+"/"+"datanewchi45.csv"
pa5=p+"/"+"dataset"+"/"+"datanewchi34.csv"
result_array = np.empty((0, 100))
ph = sound
files = glob.glob(ph)
result_array = np.empty((0, 27))
try:
for soundi in files:
objects= run_file(sourcerun, -20, 2, 0.3, "yes", soundi, path, 80, 400, 0.01, capture_output=True)
#print (objects[0]) # This will print the info from the sound object, and objects[0] is a parselmouth.Sound object
z1=( objects[1]) # This will print the info from the textgrid object, and objects[1] is a parselmouth.Data object with a TextGrid inside
z3=z1.strip().split()
z2=np.array([z3])
result_array=np.append(result_array,[z3], axis=0)
np.savetxt(pa1,result_array, fmt='%s',delimiter=',')
#Data and features analysis
df = pd.read_csv(pa1, names = ['avepauseduratin','avelongpause','speakingtot','avenumberofwords','articulationrate','inpro','f1norm','mr','q25',
'q50','q75','std','fmax','fmin','vowelinx1','vowelinx2','formantmean','formantstd','nuofwrds','npause','ins',
'fillerratio','xx','xxx','totsco','xxban','speakingrate'],na_values='?')
import sys
def my_except_hook(exctype, value, traceback):
print('There has been an error in the system')
sys.excepthook = my_except_hook
import warnings
if not sys.warnoptions:
warnings.simplefilter("ignore")
sound=p+"/"+"dataset"+"/"+"audioFiles"+"/"+m+".wav"
sourcerun=p+"/"+"dataset"+"/"+"essen"+"/"+"MLTRNL.praat"
path=p+"/"+"dataset"+"/"+"audioFiles"+"/"
pa1=p+"/"+"dataset"+"/"+"datanewchi23.csv"
pa7=p+"/"+"dataset"+"/"+"datanewchi45.csv"
pa5=p+"/"+"dataset"+"/"+"datanewchi34.csv"
result_array = np.empty((0, 100))
ph = sound
files = glob.glob(ph)
result_array = np.empty((0, 27))
try:
for soundi in files:
objects= run_file(sourcerun, -20, 2, 0.3, "yes", soundi, path, 80, 400, 0.01, capture_output=True)
#print (objects[0]) # This will print the info from the sound object, and objects[0] is a parselmouth.Sound object
z1=( objects[1]) # This will print the info from the textgrid object, and objects[1] is a parselmouth.Data object with a TextGrid inside
z3=z1.strip().split()
z2=np.array([z3])
result_array=np.append(result_array,[z3], axis=0)
np.savetxt(pa1,result_array, fmt='%s',delimiter=',')
#Data and features analysis
df = pd.read_csv(pa1, names = ['avepauseduratin','avelongpause','speakingtot','avenumberofwords','articulationrate','inpro','f1norm','mr','q25',
'q50','q75','std','fmax','fmin','vowelinx1','vowelinx2','formantmean','formantstd','nuofwrds','npause','ins',
'fillerratio','xx','xxx','totsco','xxban','speakingrate'],na_values='?')

scoreMLdataset=df.drop(['xxx','xxban'], axis=1)
scoreMLdataset.to_csv(pa7, header=False,index = False)
newMLdataset=df.drop(['avenumberofwords','f1norm','inpro','q25','q75','vowelinx1','nuofwrds','npause','xx','totsco','xxban','speakingrate','fillerratio'], axis=1)
newMLdataset.to_csv(pa5, header=False,index = False)
namess=nms = ['avepauseduratin','avelongpause','speakingtot','articulationrate','mr',
'q50','std','fmax','fmin','vowelinx2','formantmean','formantstd','ins',
'xxx']
df1 = pd.read_csv(pa5,
names = namess)
df33=df1.drop(['xxx'], axis=1)
array = df33.values
array=np.log(array)
x = array[:,0:13]
scoreMLdataset=df.drop(['xxx','xxban'], axis=1)
scoreMLdataset.to_csv(pa7, header=False,index = False)
newMLdataset=df.drop(['avenumberofwords','f1norm','inpro','q25','q75','vowelinx1','nuofwrds','npause','xx','totsco','xxban','speakingrate','fillerratio'], axis=1)
newMLdataset.to_csv(pa5, header=False,index = False)
namess=nms = ['avepauseduratin','avelongpause','speakingtot','articulationrate','mr',
'q50','std','fmax','fmin','vowelinx2','formantmean','formantstd','ins',
'xxx']
df1 = pd.read_csv(pa5,
names = namess)
df33=df1.drop(['xxx'], axis=1)
array = df33.values
array=np.log(array)
x = array[:,0:13]

def myspp(bp,bg):
sound=bg+"/"+"dataset"+"/"+"audioFiles"+"/"+bp+".wav"
sourcerun=bg+"/"+"dataset"+"/"+"essen"+"/"+"myspsolution.praat"
path=bg+"/"+"dataset"+"/"+"audioFiles"+"/"
objects= run_file(sourcerun, -20, 2, 0.3, "yes",sound,path, 80, 400, 0.01, capture_output=True)
print (objects[0]) # This will print the info from the sound object, and objects[0] is a parselmouth.Sound object
z1=str( objects[1]) # This will print the info from the textgrid object, and objects[1] is a parselmouth.Data object with a TextGrid inside
z2=z1.strip().split()
z3=int(z2[13]) # will be the integer number 10
z4=float(z2[14]) # will be the floating point number 8.3
db= binom.rvs(n=10,p=z4,size=10000)
a=np.array(db)
b=np.mean(a)*100/10
return b
bp=m
bg=p
bi=myspp(bp,bg)
if bi<85:
input("Try again, unnatural-sounding speech detected. No further result. Press any key to exit.")
exit()
filename=p+"/"+"dataset"+"/"+"essen"+"/"+"CART_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("58% accuracy ",predictions)
def myspp(bp,bg):
sound=bg+"/"+"dataset"+"/"+"audioFiles"+"/"+bp+".wav"
sourcerun=bg+"/"+"dataset"+"/"+"essen"+"/"+"myspsolution.praat"
path=bg+"/"+"dataset"+"/"+"audioFiles"+"/"
objects= run_file(sourcerun, -20, 2, 0.3, "yes",sound,path, 80, 400, 0.01, capture_output=True)
print (objects[0]) # This will print the info from the sound object, and objects[0] is a parselmouth.Sound object
z1=str( objects[1]) # This will print the info from the textgrid object, and objects[1] is a parselmouth.Data object with a TextGrid inside
z2=z1.strip().split()
z3=int(z2[13]) # will be the integer number 10
z4=float(z2[14]) # will be the floating point number 8.3
db= binom.rvs(n=10,p=z4,size=10000)
a=np.array(db)
b=np.mean(a)*100/10
return b
bp=m
bg=p
bi=myspp(bp,bg)
if bi<85:
input("Try again, unnatural-sounding speech detected. No further result. Press any key to exit.")
exit()
filename=p+"/"+"dataset"+"/"+"essen"+"/"+"CART_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("58% accuracy ",predictions)

filename=p+"/"+"dataset"+"/"+"essen"+"/"+"KNN_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("65% accuracy ",predictions)
filename=p+"/"+"dataset"+"/"+"essen"+"/"+"KNN_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("65% accuracy ",predictions)

filename=p+"/"+"dataset"+"/"+"essen"+"/"+"LDA_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("70% accuracy ",predictions)
filename=p+"/"+"dataset"+"/"+"essen"+"/"+"LDA_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("70% accuracy ",predictions)

filename=p+"/"+"dataset"+"/"+"essen"+"/"+"LR_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("67% accuracy ",predictions)
filename=p+"/"+"dataset"+"/"+"essen"+"/"+"LR_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("67% accuracy ",predictions)

filename=p+"/"+"dataset"+"/"+"essen"+"/"+"NB_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("64% accuracy ",predictions)
filename=p+"/"+"dataset"+"/"+"essen"+"/"+"NB_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("64% accuracy ",predictions)

filename=p+"/"+"dataset"+"/"+"essen"+"/"+"SVN_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("63% accuracy ",predictions)
except:
print ("Try again the sound of the audio was not clear")
filename=p+"/"+"dataset"+"/"+"essen"+"/"+"SVN_model.sav"
model = pickle.load(open(filename, 'rb'))
predictions = model.predict(x)
print("63% accuracy ",predictions)
except:
print ("Try again the sound of the audio was not clear")