shithub: opus

Info  •  Files  •  Log  •  Branches

Add prediction

--- a/dnn/lpcnet.py

+++ b/dnn/lpcnet.py

@@ -10,7 +10,7 @@

 import h5py

 import sys

-rnn_units=512

+rnn_units=64

 pcm_bits = 8

 pcm_levels = 2**pcm_bits

 nb_used_features = 38

@@ -41,7 +41,7 @@

         }

 def new_wavernn_model():

-    pcm = Input(shape=(None, 1))

+    pcm = Input(shape=(None, 2))

     pitch = Input(shape=(None, 1))

     feat = Input(shape=(None, nb_used_features))

     dec_feat = Input(shape=(None, 32))

@@ -61,7 +61,7 @@

         cpitch = pitch

     embed = Embedding(256, 128, embeddings_initializer=PCMInit())

-    cpcm = Reshape((-1, 128))(embed(pcm))

+    cpcm = Reshape((-1, 128*2))(embed(pcm))

     cfeat = fconv2(fconv1(feat))

--- a/dnn/train_wavenet_audio.py

+++ b/dnn/train_wavenet_audio.py

@@ -25,8 +25,10 @@

 model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy'])

 model.summary()

-pcmfile = sys.argv[1]

+exc_file = sys.argv[1]

 feature_file = sys.argv[2]

+pred_file = sys.argv[3]

+pcm_file = sys.argv[4]

 frame_size = 160

 nb_features = 54

 nb_used_features = wavenet.nb_used_features

@@ -33,8 +35,8 @@

 feature_chunk_size = 15

 pcm_chunk_size = frame_size*feature_chunk_size

-data = np.fromfile(pcmfile, dtype='int16')

-data = np.minimum(127, lin2ulaw(data[80:]/32768.))

+data = np.fromfile(pcm_file, dtype='int16')

+data = np.minimum(127, lin2ulaw(data/32768.))

 nb_frames = len(data)//pcm_chunk_size

 features = np.fromfile(feature_file, dtype='float32')

@@ -46,6 +48,13 @@

 in_data = in_data + np.random.randint(-1, 1, len(data))

 features = np.reshape(features, (nb_frames*feature_chunk_size, nb_features))

+

+pred = np.fromfile(pred_file, dtype='int16')

+pred = pred[:nb_frames*pcm_chunk_size]

+pred = np.minimum(127, lin2ulaw(pred/32768.))

+pred = pred + np.random.randint(-1, 1, len(data))

+

+

 pitch = 1.*data

 pitch[:320] = 0

 for i in range(2, nb_frames*feature_chunk_size):

@@ -60,7 +69,10 @@

 out_data = (out_data.astype('int16')+128).astype('uint8')

 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')

+in_data = np.concatenate([in_data, pred], axis=-1)

 #in_data = np.concatenate([in_data, in_pitch], axis=-1)

@@ -68,7 +80,7 @@

 # f.create_dataset('data', data=in_data[:50000, :, :])

 # f.create_dataset('feat', data=features[:50000, :, :])

-checkpoint = ModelCheckpoint('wavenet3g_{epoch:02d}.h5')

+checkpoint = ModelCheckpoint('wavenet3h9_{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'])

-- 

⑨