eden-emu/opus
15
0
Fork 0
mirror of https://github.com/xiph/opus.git synced 2025-05-31 07:37:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

pitch embedding

Browse source
This commit is contained in:
Jean-Marc Valin 2018-10-02 21:17:34 -04:00
parent 2d74d3189c
commit 639766b322
3 changed files with 11 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

10
dnn/lpcnet.py
View file

@ -46,6 +46,7 @@ def new_wavernn_model():
exc = Input(shape=(None, 1))
pitch = Input(shape=(None, 1))
feat = Input(shape=(None, nb_used_features))
pitch = Input(shape=(None, 1))
dec_feat = Input(shape=(None, 32))
dec_state = Input(shape=(rnn_units,))
@ -67,7 +68,10 @@ def new_wavernn_model():
embed2 = Embedding(256, embed_size, embeddings_initializer=PCMInit())
cexc = Reshape((-1, embed_size))(embed2(exc))
cfeat = fconv2(fconv1(feat))
pembed = Embedding(256, 64)
cat_feat = Concatenate()([feat, Reshape((-1, 64))(pembed(pitch))])
cfeat = fconv2(fconv1(cat_feat))
rep = Lambda(lambda x: K.repeat_elements(x, 160, 1))
@ -77,8 +81,8 @@ def new_wavernn_model():
gru_out, state = rnn(rnn_in)
ulaw_prob = md(gru_out)
model = Model([pcm, exc, feat], ulaw_prob)
encoder = Model(feat, cfeat)
model = Model([pcm, exc, feat, pitch], ulaw_prob)
encoder = Model([feat, pitch], cfeat)
dec_rnn_in = Concatenate()([cpcm, cexc, dec_feat])
dec_gru_out, state = rnn(dec_rnn_in, initial_state=dec_state)

2
dnn/test_wavenet_audio.py
View file

@ -60,7 +60,7 @@ out_data = (out_data.astype('int16')+128).astype('uint8')
features = np.reshape(features, (nb_frames, feature_chunk_size, nb_features))
features = features[:, :, :]
periods = (50*features[:,:,36:37]+100).astype('int16')
in_data = np.reshape(in_data, (nb_frames*pcm_chunk_size, 1))
out_data = np.reshape(data, (nb_frames*pcm_chunk_size, 1))

5
dnn/train_wavenet_audio.py
View file

@ -94,6 +94,7 @@ features = np.reshape(features, (nb_frames, feature_chunk_size, nb_features))
features = features[:, :, :nb_used_features]
pred = np.reshape(pred, (nb_frames, pcm_chunk_size, 1))
pred = (pred.astype('int16')+128).astype('uint8')
periods = (50*features[:,:,36:37]+100).astype('int16')
in_data = np.concatenate([in_data, pred], axis=-1)
@ -103,8 +104,8 @@ 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('wavenet4d3_{epoch:02d}.h5')
checkpoint = ModelCheckpoint('wavenet4e_{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'])
model.fit([in_data, in_exc, features], out_data, batch_size=batch_size, epochs=30, validation_split=0.2, callbacks=[checkpoint])
model.fit([in_data, in_exc, features, periods], out_data, batch_size=batch_size, epochs=30, validation_split=0.2, callbacks=[checkpoint])