eden-emu/opus
15
0
Fork 0
mirror of https://github.com/xiph/opus.git synced 2025-05-21 10:58:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Making it easier to change the frame size

Browse source
This commit is contained in:
Jean-Marc Valin 2019-01-18 15:08:06 -05:00
parent 38cd5cf08f
commit dc082d7c1c
4 changed files with 7 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
dnn/dump_data.c
View file

@ -313,7 +313,7 @@ int main(int argc, char **argv) {
} }
last_silent = silent; last_silent = silent;
} }
if (count>=5000000 && one_pass_completed) break; if (count*FRAME_SIZE_5MS>=10000000 && one_pass_completed) break;
if (training && ++gain_change_count > 2821) { if (training && ++gain_change_count > 2821) {
float tmp; float tmp;
speech_gain = pow(10., (-20+(rand()%40))/20.); speech_gain = pow(10., (-20+(rand()%40))/20.);

4
dnn/lpcnet.py
View file

@ -36,6 +36,7 @@ import numpy as np
import h5py import h5py
import sys import sys
frame_size = 160
pcm_bits = 8 pcm_bits = 8
embed_size = 128 embed_size = 128
pcm_levels = 2**pcm_bits pcm_levels = 2**pcm_bits
@ -139,7 +140,7 @@ def new_lpcnet_model(rnn_units1=384, rnn_units2=16, nb_used_features = 38, use_g
cfeat = fdense2(fdense1(cfeat)) cfeat = fdense2(fdense1(cfeat))
rep = Lambda(lambda x: K.repeat_elements(x, 160, 1)) rep = Lambda(lambda x: K.repeat_elements(x, frame_size, 1))
if use_gpu: if use_gpu:
rnn = CuDNNGRU(rnn_units1, return_sequences=True, return_state=True, name='gru_a') rnn = CuDNNGRU(rnn_units1, return_sequences=True, return_state=True, name='gru_a')
@ -158,6 +159,7 @@ def new_lpcnet_model(rnn_units1=384, rnn_units2=16, nb_used_features = 38, use_g
model.rnn_units1 = rnn_units1 model.rnn_units1 = rnn_units1
model.rnn_units2 = rnn_units2 model.rnn_units2 = rnn_units2
model.nb_used_features = nb_used_features model.nb_used_features = nb_used_features
model.frame_size = frame_size
encoder = Model([feat, pitch], cfeat) encoder = Model([feat, pitch], cfeat)

2
dnn/test_lpcnet.py
View file

@ -47,7 +47,7 @@ model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=
feature_file = sys.argv[1] feature_file = sys.argv[1]
out_file = sys.argv[2] out_file = sys.argv[2]
frame_size = 160 frame_size = model.frame_size
nb_features = 55 nb_features = 55
nb_used_features = model.nb_used_features nb_used_features = model.nb_used_features

4
dnn/train_lpcnet.py
View file

@ -58,7 +58,7 @@ model.summary()
feature_file = sys.argv[1] feature_file = sys.argv[1]
pcm_file = sys.argv[2] # 16 bit unsigned short PCM samples pcm_file = sys.argv[2] # 16 bit unsigned short PCM samples
frame_size = 160 frame_size = model.frame_size
nb_features = 55 nb_features = 55
nb_used_features = model.nb_used_features nb_used_features = model.nb_used_features
feature_chunk_size = 15 feature_chunk_size = 15
@ -97,7 +97,7 @@ del sig
del pred del pred
# dump models to disk as we go # dump models to disk as we go
checkpoint = ModelCheckpoint('lpcnet20c_384_10_G16_{epoch:02d}.h5') checkpoint = ModelCheckpoint('lpcnet20g_384_10_G16_{epoch:02d}.h5')
#model.load_weights('lpcnet9b_384_10_G16_01.h5') #model.load_weights('lpcnet9b_384_10_G16_01.h5')
model.compile(optimizer=Adam(0.001, amsgrad=True, decay=5e-5), loss='sparse_categorical_crossentropy') model.compile(optimizer=Adam(0.001, amsgrad=True, decay=5e-5), loss='sparse_categorical_crossentropy')