[英]Python beginner ML project issues
所以我復制了一些代碼來嘗試在 python 中弄清楚機器學習(鏈接 = https://data-flair.training/blogs/python-mini-project-speech-emotion-recognition )。 總的來說效果很好,但現在我不知道如何使用它(輸入我自己的文件並分析它)。
import librosa
import numpy as np
import soundfile
import sklearn
import os, glob, pickle
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import accuracy_score
def extract_feture(filepath,mfcc,chroma,mel):
with soundfile.SoundFile(filepath) as sound_file:
X = sound_file.read(dtype="float32")
sample_rate=sound_file.samplerate
if chroma:
stft = np.abs(librosa.stft(X))
result = np.array([])
if mfcc:
mfccs = np.mean(librosa.feature.mfcc(y=X, sr=sample_rate, n_mfcc=40) .T, axis=0)
result = np.hstack((result, mfccs))
if chroma:
chroma = np.mean(librosa.feature.chroma_stft(S=stft, sr=sample_rate).T, axis=0)
result = np.hstack((result, chroma))
if mel:
mel = np.mean(librosa.feature.melspectrogram(X, sr= sample_rate).T,axis=0)
result = np.hstack((result, mel))
return result
emotions = {
'01':'neutral',
'02':'calm',
'03':'happy',
'04':'sad',
'05': 'angry',
'06': 'fearful',
'07': 'disgust',
'08': 'surprised'
}
observed_emotions =['calm', 'happy', 'fearful', 'disgust']
def load_data(test_size=0.2):
x, y = [], []
for file in glob.glob("/home/adobug2/Documents/ravdess-data/Actor_*/*.wav"):
file_name = os.path.basename(file)
emotion = emotions[file_name.split("-")[2]]
if emotion not in observed_emotions:
continue
feature = extract_feture(file, mfcc=True, chroma=True, mel=True)
x.append(feature)
y.append(emotion)
return train_test_split(np.array(x), y, test_size=test_size, random_state=9)
x_train,x_test,y_train,y_test=load_data(test_size=0.25)
print((x_train.shape[0], x_test.shape[0]))
print(f'Features extracted: {x_train.shape[1]}')
model=MLPClassifier(alpha=0.01, batch_size=256, epsilon=1e-08, hidden_layer_sizes=(300,), learning_rate='adaptive', max_iter=500)
model.fit(x_train,y_train)
y_pred=model.predict(x_test)
accuracy=accuracy_score(y_true=y_test, y_pred=y_pred)
print("Accuracy: {:.2f}%".format(accuracy*100))
在您的新音頻文件上使用model.predict()
。 那應該會返回您想要的 output。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.