storytold/torchscript-models
2
0
Fork 0
mirror of https://github.com/storytold/torchscript-models.git synced 2026-10-19 07:42:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

uncommitted changes

Browse Source
This commit is contained in:
Brandon Thomas
2020-06-14 23:19:34 -04:00
parent 7a5e0033db
commit 788eef5e1a
2 changed files with 9 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
glow-tts-jaywalnut/wrap_glow_model.py
+8 -6
View File
@@ -14,7 +14,7 @@ from text.symbols import symbols
#from apex import amp
#from apex.parallel import DistributedDataParallel as DDP
# Data
# Data
import numpy as np
from text import text_to_sequence, cmudict
@@ -35,8 +35,7 @@ def load(model_checkpoint_path):
with torch.no_grad():
# NB(bt): This should fix the following:
# RuntimeError: Cannot insert a Tensor that requires grad as a constant.
# Consider making it a parameter or input, or detaching the gradient Tensor:
# RuntimeError: Cannot insert a Tensor that requires grad as a constant.
model = models.FlowGenerator(
len(symbols),
out_channels=hps.data.n_mel_channels,
@@ -50,15 +49,18 @@ def load(model_checkpoint_path):
#model_checkpoint_path = '/home/bt/models/glow-tts-jaywalnut/pretrained.pth'
model_checkpoint_path = '/home/bt/models/glow-tts-jaywalnut/G_1007.pth'
model_checkpoint_path = '/home/bt/models/glow-tts-jaywalnut/glow_tts_ljs_txlearn_arpabet_2020-06-01_G_1689.pth'
model_checkpoint_path = '/home/bt/models/glow-tts-jaywalnut/glow_tts_ljs_txlearn_arpabet_2020-06-01_G_2590.pth'
model_checkpoint_path = '/home/bt/models/glow-tts-jaywalnut/glow_tts_ljs_txlearn_arpabet_2020-06-01_G_3614.pth'
hps, glow_model = load(model_checkpoint_path)
output_filename = 'output.torchjit'
output_filename = 'glow_tts_ljs_txlearn_arpabet_2020-06-01_G_2590.torchjit'
output_filename = 'glow_tts_ljs_txlearn_arpabet_2020-06-01_G_3614.torchjit'
cmu_dict = cmudict.CMUDict(hps.data.cmudict_path)
tst_stn = "my name is donald trump and I am the president of the united states, you should respect me"
tst_stn = "This is a test of the machine learning model. How does this sound?"
seq = text_to_sequence(tst_stn, ['english_cleaners'], cmu_dict)
sequence = np.array(seq)[None, :] # NB: None adds a new axis.
print("".join([symbols[c] for c in sequence[0]]))