I am making voice detection by using Tensorflow. The computer will be recording my voice and when I say:" Hey Jarvis" it will print "voice has been detected". However, the program is not working properly, when I say "Hey Jarvis" it always prints: "voice not detected". I don't know how to fix it I have tried many ways but it not working. Hope someone can help me thanks.
Here is my code:
######## IMPORTS ##########
import sounddevice as sd
from scipy.io.wavfile import write
import librosa
import numpy as np
from tensorflow.keras.models import load_model
####### ALL CONSTANTS #####
fs = 44100
seconds = 2
filename = "C:\\Users\\adamn\Documents\\voice detection\\WakeWordDetection-master\\WakeWordDetection-master\\prediction.wav"
class_names = ["Wake Word NOT Detected", "Wake Word Detected"]
##### LOADING OUR SAVED MODEL and PREDICTING ###
model = load_model("C:\\Users\\adamn\Documents\\voice detection\\WakeWordDetection-master\\WakeWordDetection-master\\saved_model\\WWD2.h5")
print("Prediction Started: ")
i = 0
while True:
print("Say Now: ")
myrecording = sd.rec(int(seconds * fs), samplerate=fs, channels=2)
sd.wait()
write(filename, fs, myrecording)
audio, sample_rate = librosa.load(filename)
mfcc = librosa.feature.mfcc(y=audio, sr=sample_rate, n_mfcc=40)
mfcc_processed = np.mean(mfcc.T, axis=0)
prediction = model.predict(np.expand_dims(mfcc_processed, axis=0))
if prediction[:, 1] > 0.10:
print(f"Wake Word Detected for ({i})")
print("Confidence:", prediction[:, 1])
i += 1
else:
print(f"Wake Word NOT Detected")
print("Confidence:", prediction[:, 0])
I said: "Hey Jarvis" four times but it cannot detect the word. Here is the terminal
PS C:\Users\adamn\Documents\voice detection\WakeWordDetection-master> & C:/Users/adamn/AppData/Local/Programs/Python/Python310/python.exe "c:/Users/adamn/Documents/voice detection/WakeWordDetection-master/WakeWordDetection-master/prediction.py"
2022-12-30 11:55:29.369866: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-12-30 11:55:29.370141: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2022-12-30 11:55:30.987283: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found
2022-12-30 11:55:30.987446: W tensorflow/stream_executor/cuda/cuda_driver.cc:263] failed call to cuInit: UNKNOWN ERROR (303)
2022-12-30 11:55:30.990920: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: KhoaLaptop
2022-12-30 11:55:30.991644: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: KhoaLaptop
2022-12-30 11:55:30.992261: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Prediction Started:
Say Now:
1/1 [==============================] - 0s 60ms/step
Wake Word NOT Detected
Confidence: [1.]
Say Now:
1/1 [==============================] - 0s 14ms/step
Wake Word NOT Detected
Confidence: [1.]
Say Now:
1/1 [==============================] - 0s 13ms/step
Wake Word NOT Detected
Confidence: [1.]
Say Now:
1/1 [==============================] - 0s 11ms/step
Wake Word NOT Detected
Confidence: [1.]
Say Now:
