I have tried following this link to extract audio features:
https://colab.research.google.com/drive/1TbX92UL9sYWbdwdGE0rJ9owmezB-Rl1C
but i unable to input raw audio files and get the 128 extracted features.
How can i extract the features
You can try using tensorflow model hub
import tensorflow as tf
import tensorflow_hub as hub
import numpy as np
import librosa
# Load the model.
vggmodel = hub.load('https://tfhub.dev/google/vggish/1')
def embedding_from_fn(fn):
x, sr = librosa.load(fn,sr=None)
x_16k = librosa.resample(x,sr,16000) #resample to 16KHz
embedding = np.array(vggmodel(x_16k))
return embedding
embedding = embedding_from_fn(df['fn'].values[0]).shape
Thank you,
You can try using tensorflow model hub
import tensorflow as tf
import tensorflow_hub as hub
import numpy as np
import librosa
# Load the model.
vggmodel = hub.load('https://tfhub.dev/google/vggish/1')
def embedding_from_fn(fn):
x, sr = librosa.load(fn,sr=None)
x_16k = librosa.resample(x,sr,16000) #resample to 16KHz
embedding = np.array(vggmodel(x_16k))
return embedding
embedding = embedding_from_fn(df['fn'].values[0]).shape
Thank you,