aravindpai / speech-recognition Goto Github PK

import webbrowser
import speech_recognition as sr

r = sr.Recognizer()
while True:
with sr.Microphone() as source:
print('Hola, soy tu asistente por voz: ')
audio = r.listen(source)

    try:
        text = r.recognize_google(audio)
        print('Has dicho: {}'.format(text))
        print(text)
        if "Amazon" in text:
            webbrowser.open('http://amazon.es')
        if "noticias" in text:
            webbrowser.open('http://noticiasfinancieras.info')
        if "que tal" in text:
            print("Bien y tu?")
    except:
        print('No te he entendido')

I have this python code developed in Visual Studio Code and every time I try to run it the following exception appears and i dont know why: self.stream.close() --> AttributeError: 'NoneType' object has no attribute 'close'

i am using python 3.6 on jupyter notebook and i install librosa but when i want to import librosa it gives me a error

After reshaping the array from 2D to 3D and tried to allocate train and test data, sklearn complains that it's excepting 2D. The following line throws error:

from sklearn.model_selection import train_test_split
x_tr, x_val, y_tr, y_val = train_test_split(np.array(all_wave),np.array(y),stratify=y,test_size = 0.2,random_state=777,shuffle=True)

I have downloaded the train.7z file. And have found that I am not able to play any of the wave files in the dataset. Also, librosa is not able to import it. Kindly post any solution if you have come across this.

Is it work on sentences?
I have the data set that includes sentences.

Hi! I have a problem in this lines
from keras.models import load_model
model=load_model('best_model.hdf5')
this is what ı am getting;
can you help me please :)

OSError Traceback (most recent call last)
in
1 from keras.models import load_model
----> 2 model=load_model('best_model.hdf5')

~\anaconda3\envs\speech\lib\site-packages\tensorflow\python\keras\saving\save.py in load_model(filepath, custom_objects, compile, options)
184 filepath = path_to_string(filepath)
185 if isinstance(filepath, six.string_types):
--> 186 loader_impl.parse_saved_model(filepath)
187 return saved_model_load.load(filepath, compile, options)
188

~\anaconda3\envs\speech\lib\site-packages\tensorflow\python\saved_model\loader_impl.py in parse_saved_model(export_dir)
108 raise IOError("Cannot parse file %s: %s." % (path_to_pbtxt, str(e)))
109 else:
--> 110 raise IOError("SavedModel file does not exist at: %s/{%s|%s}" %
111 (export_dir,
112 constants.SAVED_MODEL_FILENAME_PBTXT,

In this Post of Speech to Text Model, every parameter is observed. But the Final Cross Confusion Matrix is not implemented.

The Prediction Tags are generated for only a random sample. Can you help me on how to create an array for all the actual tags and Predicted Tags?

I am a budding learner in this field, and could really use some help.

Value error : can not reshape array of 1d to 3d

Thank you for your work and sharing.