mirror of
https://github.com/xiph/opus.git
synced 2025-05-18 17:38:29 +00:00
82 lines
2.7 KiB
Python
Executable file
82 lines
2.7 KiB
Python
Executable file
#!/usr/bin/python3
|
|
|
|
import lpcnet
|
|
import sys
|
|
import numpy as np
|
|
from keras.optimizers import Adam
|
|
from keras.callbacks import ModelCheckpoint
|
|
from ulaw import ulaw2lin, lin2ulaw
|
|
import keras.backend as K
|
|
import h5py
|
|
from adadiff import Adadiff
|
|
|
|
#import tensorflow as tf
|
|
#from keras.backend.tensorflow_backend import set_session
|
|
#config = tf.ConfigProto()
|
|
#config.gpu_options.per_process_gpu_memory_fraction = 0.28
|
|
#set_session(tf.Session(config=config))
|
|
|
|
nb_epochs = 40
|
|
batch_size = 64
|
|
|
|
model, enc, dec = lpcnet.new_wavernn_model()
|
|
model.compile(optimizer=Adadiff(), loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy'])
|
|
#model.summary()
|
|
|
|
pcmfile = sys.argv[1]
|
|
feature_file = sys.argv[2]
|
|
frame_size = 160
|
|
nb_features = 54
|
|
nb_used_features = lpcnet.nb_used_features
|
|
feature_chunk_size = 15
|
|
pcm_chunk_size = frame_size*feature_chunk_size
|
|
|
|
data = np.fromfile(pcmfile, dtype='int8')
|
|
nb_frames = len(data)//pcm_chunk_size
|
|
|
|
features = np.fromfile(feature_file, dtype='float32')
|
|
|
|
data = data[:nb_frames*pcm_chunk_size]
|
|
features = features[:nb_frames*feature_chunk_size*nb_features]
|
|
|
|
in_data = np.concatenate([data[0:1], data[:-1]])/16.;
|
|
|
|
features = np.reshape(features, (nb_frames, feature_chunk_size, nb_features))
|
|
|
|
in_data = np.reshape(in_data, (nb_frames*pcm_chunk_size, 1))
|
|
out_data = np.reshape(data, (nb_frames*pcm_chunk_size, 1))
|
|
|
|
|
|
model.load_weights('lpcnet1i_30.h5')
|
|
|
|
order = 16
|
|
|
|
pcm = 0.*out_data
|
|
exc = out_data-0
|
|
pitch = np.zeros((1, 1, 1), dtype='float32')
|
|
fexc = np.zeros((1, 1, 1), dtype='float32')
|
|
iexc = np.zeros((1, 1, 1), dtype='int16')
|
|
state = np.zeros((1, lpcnet.rnn_units), dtype='float32')
|
|
for c in range(1, nb_frames):
|
|
cfeat = enc.predict(features[c:c+1, :, :nb_used_features])
|
|
for fr in range(1, feature_chunk_size):
|
|
f = c*feature_chunk_size + fr
|
|
a = features[c, fr, nb_used_features+1:]
|
|
|
|
#print(a)
|
|
gain = 1.;
|
|
period = int(50*features[c, fr, 36]+100)
|
|
period = period - 4
|
|
for i in range(frame_size):
|
|
pitch[0, 0, 0] = exc[f*frame_size + i - period, 0]
|
|
fexc[0, 0, 0] = exc[f*frame_size + i - 1]
|
|
#print(cfeat.shape)
|
|
p, state = dec.predict([fexc, pitch, cfeat[:, fr:fr+1, :], state])
|
|
p = p/(1e-5 + np.sum(p))
|
|
#print(np.sum(p))
|
|
iexc[0, 0, 0] = np.argmax(np.random.multinomial(1, p[0,0,:], 1))-128
|
|
exc[f*frame_size + i] = iexc[0, 0, 0]/16.
|
|
#out_data[f*frame_size + i, 0] = iexc[0, 0, 0]
|
|
pcm[f*frame_size + i, 0] = gain*iexc[0, 0, 0] - sum(a*pcm[f*frame_size + i - 1:f*frame_size + i - order-1:-1, 0])
|
|
print(iexc[0, 0, 0], out_data[f*frame_size + i, 0], pcm[f*frame_size + i, 0])
|
|
|