eden-emu/opus
15
0
Fork 0
mirror of https://github.com/xiph/opus.git synced 2025-05-29 22:57:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Training seems to work

Browse source
This commit is contained in:
Jean-Marc Valin 2018-08-16 22:43:13 -04:00
parent 785a2b2e84
commit 87cd75f6f4
2 changed files with 14 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
dnn/lpcnet.py
View file

@ -41,7 +41,7 @@ class PCMInit(Initializer):
} }
def new_wavernn_model(): def new_wavernn_model():
pcm = Input(shape=(None, 1)) pcm = Input(shape=(None, 2))
pitch = Input(shape=(None, 1)) pitch = Input(shape=(None, 1))
feat = Input(shape=(None, nb_used_features)) feat = Input(shape=(None, nb_used_features))
dec_feat = Input(shape=(None, 32)) dec_feat = Input(shape=(None, 32))
@ -61,7 +61,7 @@ def new_wavernn_model():
cpitch = pitch cpitch = pitch
embed = Embedding(256, 128, embeddings_initializer=PCMInit()) embed = Embedding(256, 128, embeddings_initializer=PCMInit())
cpcm = Reshape((-1, 128))(embed(pcm)) cpcm = Reshape((-1, 128*2))(embed(pcm))
cfeat = fconv2(fconv1(feat)) cfeat = fconv2(fconv1(feat))

14
dnn/train_wavenet_audio.py
View file

@ -51,8 +51,18 @@ features = np.reshape(features, (nb_frames*feature_chunk_size, nb_features))
pred = np.fromfile(pred_file, dtype='int16') pred = np.fromfile(pred_file, dtype='int16')
pred = pred[:nb_frames*pcm_chunk_size] pred = pred[:nb_frames*pcm_chunk_size]
pred_in = 32768.*ulaw2lin(data)
for i in range(2, nb_frames*feature_chunk_size):
pred[i*frame_size:(i+1)*frame_size] = 0
if i % 100000 == 0:
print(i)
for k in range(16):
pred[i*frame_size:(i+1)*frame_size] = pred[i*frame_size:(i+1)*frame_size] - \
pred_in[i*frame_size-k-1:(i+1)*frame_size-k-1]*features[i, nb_features-16+k]
pred = np.minimum(127, lin2ulaw(pred/32768.)) pred = np.minimum(127, lin2ulaw(pred/32768.))
pred = pred + np.random.randint(-1, 1, len(data)) #pred = pred + np.random.randint(-1, 1, len(data))
pitch = 1.*data pitch = 1.*data
@ -72,7 +82,7 @@ features = features[:, :, :nb_used_features]
pred = np.reshape(pred, (nb_frames, pcm_chunk_size, 1)) pred = np.reshape(pred, (nb_frames, pcm_chunk_size, 1))
pred = (pred.astype('int16')+128).astype('uint8') pred = (pred.astype('int16')+128).astype('uint8')
#in_data = np.concatenate([in_data, pred], axis=-1) in_data = np.concatenate([in_data, pred], axis=-1)
#in_data = np.concatenate([in_data, in_pitch], axis=-1) #in_data = np.concatenate([in_data, in_pitch], axis=-1)