FreeDV
/
LPCNet
mirror of https://github.com/drowe67/LPCNet.git
1
0
Fork 0
Code Issues Releases Wiki Activity

...

pull/8/head
Jean-Marc Valin 2018-10-02 18:26:42 -04:00
parent fdaa047fa5
commit c8ff029a5a
No known key found for this signature in database
GPG Key ID: 5E5DD9A36F9189C8
3 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/lpcnet.py
View File

@ -10,7 +10,7 @@ import numpy as np
import h5py
import sys
rnn_units=512
rnn_units=128
pcm_bits = 8
embed_size = 128
pcm_levels = 2**pcm_bits

8
src/test_wavenet_audio.py
View File

@ -29,7 +29,7 @@ pcmfile = sys.argv[1]
feature_file = sys.argv[2]
frame_size = 160
nb_features = 55
nb_used_features = wavenet.nb_used_features
nb_used_features = lpcnet.nb_used_features
feature_chunk_size = 15
pcm_chunk_size = frame_size*feature_chunk_size
@ -66,7 +66,7 @@ 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('wavenet4b_30.h5')
model.load_weights('wavenet4d2_203.h5')
order = 16
@ -92,8 +92,8 @@ for c in range(1, nb_frames):
p, state = dec.predict([fexc, iexc, cfeat[:, fr:fr+1, :], state])
#p = p*p
#p = p/(1e-18 + np.sum(p))
p = np.maximum(p-0.001, 0)
p = p/(1e-5 + np.sum(p))
p = np.maximum(p-0.001, 0).astype('float64')
p = p/(1e-8 + np.sum(p))
iexc[0, 0, 0] = np.argmax(np.random.multinomial(1, p[0,0,:], 1))
pcm[f*frame_size + i, 0] = pred + 32768*ulaw2lin(iexc[0, 0, 0]-128)

10
src/train_wavenet_audio.py
View File

@ -31,7 +31,7 @@ pred_file = sys.argv[3]
pcm_file = sys.argv[4]
frame_size = 160
nb_features = 55
nb_used_features = wavenet.nb_used_features
nb_used_features = lpcnet.nb_used_features
feature_chunk_size = 15
pcm_chunk_size = frame_size*feature_chunk_size
@ -46,7 +46,7 @@ udata = udata[:nb_frames*pcm_chunk_size]
features = features[:nb_frames*feature_chunk_size*nb_features]
in_data = np.concatenate([data[0:1], data[:-1]]);
noise = np.concatenate([np.zeros((len(data)*2//5)), np.random.randint(-1, 1, len(data)*3//5)])
noise = np.concatenate([np.zeros((len(data)*1//5)), np.random.randint(-3, 3, len(data)*1//5), np.random.randint(-2, 2, len(data)*1//5), np.random.randint(-1, 1, len(data)*2//5)])
in_data = in_data + noise
in_data = np.maximum(-127, np.minimum(127, in_data))
@ -58,8 +58,8 @@ upred = upred[:nb_frames*pcm_chunk_size]
pred_in = 32768.*ulaw2lin(in_data)
for i in range(2, nb_frames*feature_chunk_size):
upred[i*frame_size:(i+1)*frame_size] = 0
if i % 100000 == 0:
print(i)
#if i % 100000 == 0:
# print(i)
for k in range(16):
upred[i*frame_size:(i+1)*frame_size] = upred[i*frame_size:(i+1)*frame_size] - \
pred_in[i*frame_size-k:(i+1)*frame_size-k]*features[i, nb_features-16+k]
@ -103,7 +103,7 @@ in_data = np.concatenate([in_data, pred], axis=-1)
# f.create_dataset('data', data=in_data[:50000, :, :])
# f.create_dataset('feat', data=features[:50000, :, :])
checkpoint = ModelCheckpoint('wavenet4b_{epoch:02d}.h5')
checkpoint = ModelCheckpoint('wavenet4d3_{epoch:02d}.h5')
#model.load_weights('wavernn1c_01.h5')
model.compile(optimizer=Adam(0.001, amsgrad=True, decay=2e-4), loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy'])