ref: 97dcf52a01c40d7e2b845bdd974a922c5c23d462
parent: 3122b6b3bc565dc6be04977d3f2a785c30c6f6e3
author: Jean-Marc Valin <jmvalin@jmvalin.ca>
date: Mon Oct 22 09:40:11 EDT 2018
Remove no longer used files (old wavenet and LPCNet implementations)
--- a/dnn/test_lpcnet.py
+++ /dev/null
@@ -1,84 +1,0 @@
-#!/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('lpcnet3a_21.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:]
-
- #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] = 2*exc[f*frame_size + i - 1]
- #fexc[0, 0, 0] = in_data[f*frame_size + i, 0]
- #print(cfeat.shape)
- p, state = dec.predict([fexc, cfeat[:, fr:fr+1, :], state])
- #p = np.maximum(p-0.003, 0)
- 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])
-
--- a/dnn/train_lpcnet.py
+++ /dev/null
@@ -1,70 +1,0 @@
-#!/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 = 0.44
-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))
-pitch = 1.*data
-pitch[:320] = 0
-for i in range(2, nb_frames*feature_chunk_size):
- period = int(50*features[i,36]+100)
- period = period - 4
- pitch[i*frame_size:(i+1)*frame_size] = data[i*frame_size-period:(i+1)*frame_size-period]
-in_pitch = np.reshape(pitch/16., (nb_frames, pcm_chunk_size, 1))
-
-in_data = np.reshape(in_data, (nb_frames, pcm_chunk_size, 1))
-out_data = np.reshape(data, (nb_frames, pcm_chunk_size, 1))
-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]
-
-
-#in_data = np.concatenate([in_data, in_pitch], axis=-1)
-
-#with h5py.File('in_data.h5', 'w') as f:-# f.create_dataset('data', data=in_data[:50000, :, :])-# f.create_dataset('feat', data=features[:50000, :, :])-
-checkpoint = ModelCheckpoint('lpcnet3b_{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, features], out_data, batch_size=batch_size, epochs=30, validation_split=0.2, callbacks=[checkpoint])
--- a/dnn/train_wavenet.py
+++ /dev/null
@@ -1,69 +1,0 @@
-#!/usr/bin/python3
-
-import wavenet
-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
-
-import tensorflow as tf
-from keras.backend.tensorflow_backend import set_session
-config = tf.ConfigProto()
-config.gpu_options.per_process_gpu_memory_fraction = 0.44
-set_session(tf.Session(config=config))
-
-nb_epochs = 40
-batch_size = 64
-
-model = wavenet.new_wavenet_model(fftnet=True)
-model.compile(optimizer='adam', 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 = wavenet.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))
-pitch = 1.*data
-pitch[:320] = 0
-for i in range(2, nb_frames*feature_chunk_size):
- period = int(50*features[i,36]+100)
- period = period - 4
- pitch[i*frame_size:(i+1)*frame_size] = data[i*frame_size-period:(i+1)*frame_size-period]
-in_pitch = np.reshape(pitch/16., (nb_frames, pcm_chunk_size, 1))
-
-in_data = np.reshape(in_data, (nb_frames, pcm_chunk_size, 1))
-out_data = np.reshape(data, (nb_frames, pcm_chunk_size, 1))
-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]
-
-
-#in_data = np.concatenate([in_data, in_pitch], axis=-1)
-
-#with h5py.File('in_data.h5', 'w') as f:-# f.create_dataset('data', data=in_data[:50000, :, :])-# f.create_dataset('feat', data=features[:50000, :, :])-
-checkpoint = ModelCheckpoint('wavenet3c_{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, features], out_data, batch_size=batch_size, epochs=30, validation_split=0.2, callbacks=[checkpoint])
--- a/dnn/wavenet.py
+++ /dev/null
@@ -1,85 +1,0 @@
-#!/usr/bin/python3
-
-import math
-from keras.models import Model
-from keras.layers import Input, LSTM, CuDNNGRU, Dense, Embedding, Reshape, Concatenate, Lambda, Conv1D, Add, Multiply, Bidirectional, MaxPooling1D, Activation
-from keras import backend as K
-from keras.initializers import Initializer
-from keras.initializers import VarianceScaling
-from mdense import MDense
-import numpy as np
-import h5py
-import sys
-from causalconv import CausalConv
-from gatedconv import GatedConv
-
-units=128
-pcm_bits = 8
-pcm_levels = 2**pcm_bits
-nb_used_features = 38
-
-class PCMInit(Initializer):
- def __init__(self, gain=.1, seed=None):
- self.gain = gain
- self.seed = seed
-
- def __call__(self, shape, dtype=None):
- num_rows = 1
- for dim in shape[:-1]:
- num_rows *= dim
- num_cols = shape[-1]
- flat_shape = (num_rows, num_cols)
- if self.seed is not None:
- np.random.seed(self.seed)
- a = np.random.uniform(-1.7321, 1.7321, flat_shape)
- #a[:,0] = math.sqrt(12)*np.arange(-.5*num_rows+.5,.5*num_rows-.4)/num_rows
- #a[:,1] = .5*a[:,0]*a[:,0]*a[:,0]
- a = a + np.reshape(math.sqrt(12)*np.arange(-.5*num_rows+.5,.5*num_rows-.4)/num_rows, (num_rows, 1))
- return self.gain * a
-
- def get_config(self):
- return {- 'gain': self.gain,
- 'seed': self.seed
- }
-
-def new_wavenet_model(fftnet=False):
- pcm = Input(shape=(None, 1))
- pitch = Input(shape=(None, 1))
- feat = Input(shape=(None, nb_used_features))
- dec_feat = Input(shape=(None, 32))
-
- fconv1 = Conv1D(128, 3, padding='same', activation='tanh')
- fconv2 = Conv1D(32, 3, padding='same', activation='tanh')
-
- cfeat = fconv2(fconv1(feat))
-
- rep = Lambda(lambda x: K.repeat_elements(x, 160, 1))
-
- activation='tanh'
- rfeat = rep(cfeat)
- #tmp = Concatenate()([pcm, rfeat])
- embed = Embedding(256, units, embeddings_initializer=PCMInit())
- tmp = Reshape((-1, units))(embed(pcm))
- init = VarianceScaling(scale=1.5,mode='fan_avg',distribution='uniform')
- for k in range(10):
- res = tmp
- dilation = 9-k if fftnet else k
- tmp = Concatenate()([tmp, rfeat])
- c = GatedConv(units, 2, dilation_rate=2**dilation, activation='tanh', kernel_initializer=init)
- tmp = Dense(units, activation='relu')(c(tmp))
-
- '''tmp = Concatenate()([tmp, rfeat])
- c1 = CausalConv(units, 2, dilation_rate=2**dilation, activation='tanh')
- c2 = CausalConv(units, 2, dilation_rate=2**dilation, activation='sigmoid')
- tmp = Multiply()([c1(tmp), c2(tmp)])
- tmp = Dense(units, activation='relu')(tmp)'''
-
- if k != 0:
- tmp = Add()([tmp, res])
-
- md = MDense(pcm_levels, activation='softmax')
- ulaw_prob = md(tmp)
-
- model = Model([pcm, feat], ulaw_prob)
- return model
--
⑨