So I have used this git + made my own additions based on padmalcom´s branch to build a fit for me and my german sets.
Anaconda + Enviornment Python on 3.7 with all the pre req´s
I have successfully trained it on the german books padmalcom uses too, but converted them to flac instead using wav´s via batch process in flic flac
I went first with
python encoder_preprocess.py
python encoder_train.py GermanBookMale
python synthesizer_preprocess_audio.py
python synthesizer_preprocess_embeds.py
successfully.
Checkpoint path: synthesizer\saved_models\GermanBookMale\GermanBookMale.pt EXISTS, 117mb
Loading training data from: E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\train.txt EXISTS, 2,85mb
Using model: Tacotron
Using device: cuda <<< 1080 Ti 11GB
Initialising Tacotron Model...
Trainable Parameters: 30.874M
Loading weights at synthesizer\saved_models\GermanBookMale\GermanBookMale.pt
Tacotron weights loaded from step 0
Using inputs from:
E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\train.txt EXISTS, 2,85mb
E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\mels EXISTS, 2,10gb
E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\embeds EXISTS, 54mb
Traceback (most recent call last):
File "synthesizer_train.py", line 35, in
train(STAR-STAR-SYMBOLvars(args))
File "E:\DeepFakes\cleanRTVC\synthesizer\train.py", line 158, in train
for i, (texts, mels, embeds, idx) in enumerate(data_loader, 1):
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\site-packages\torch\utils\data\dataloader.py", line 278, in iter
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\site-packages\torch\utils\data\dataloader.py", line 682, in init
w.start()
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\popen_spawn_win32.py", line 89, in init
reduction.dump(process_obj, to_child)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'train..'
(GerVoice3.7) E:\DeepFakes\cleanRTVC>Traceback (most recent call last):
File "", line 1, in
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\spawn.py", line 115, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input
as add on info:
(GerVoice3.7) E:\DeepFakes\cleanRTVC>conda list torch
Name Version Build Channel
pytorch1.2.0 py3.7_cuda100_cudnn7_1 pytorch
torchfile 0.1.0 pypi_0 pypi
torchvision 0.4.0 py37_cu100 pytorch
any hint of what could go wrong here? cant point out an error?
So I have used this git + made my own additions based on padmalcom´s branch to build a fit for me and my german sets.
Anaconda + Enviornment Python on 3.7 with all the pre req´s
I have successfully trained it on the german books padmalcom uses too, but converted them to flac instead using wav´s via batch process in flic flac
I went first with python encoder_preprocess.py python encoder_train.py GermanBookMale python synthesizer_preprocess_audio.py python synthesizer_preprocess_embeds.py successfully.
Now i am failing at
(GerVoice3.7) E:\DeepFakes\cleanRTVC>python synthesizer_train.py GermanBookMale E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\ Arguments: run_id: GermanBookMale syn_dir: E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\ models_dir: synthesizer/saved_models/ save_every: 1000 backup_every: 25000 force_restart: False hparams:
Checkpoint path: synthesizer\saved_models\GermanBookMale\GermanBookMale.pt EXISTS, 117mb Loading training data from: E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\train.txt EXISTS, 2,85mb Using model: Tacotron Using device: cuda <<< 1080 Ti 11GB
Initialising Tacotron Model...
Trainable Parameters: 30.874M
Loading weights at synthesizer\saved_models\GermanBookMale\GermanBookMale.pt Tacotron weights loaded from step 0 Using inputs from: E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\train.txt EXISTS, 2,85mb E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\mels EXISTS, 2,10gb E:\DeepFakes\cleanRTVC\SV2TTS\synthesizer\embeds EXISTS, 54mb
Found 13847 samples +----------------+------------+---------------+------------------+ | Steps with r=2 | Batch Size | Learning Rate | Outputs/Step (r) | +----------------+------------+---------------+------------------+ | 20k Steps | 12 | 0.001 | 2 | +----------------+------------+---------------+------------------+
Traceback (most recent call last): File "synthesizer_train.py", line 35, in
train(STAR-STAR-SYMBOLvars(args))
File "E:\DeepFakes\cleanRTVC\synthesizer\train.py", line 158, in train
for i, (texts, mels, embeds, idx) in enumerate(data_loader, 1):
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\site-packages\torch\utils\data\dataloader.py", line 278, in iter
return _MultiProcessingDataLoaderIter(self)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\site-packages\torch\utils\data\dataloader.py", line 682, in init
w.start()
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\popen_spawn_win32.py", line 89, in init
reduction.dump(process_obj, to_child)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'train..'
(GerVoice3.7) E:\DeepFakes\cleanRTVC>Traceback (most recent call last): File "", line 1, in
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "C:\Users\User\anaconda3\envs\GerVoice3.7\lib\multiprocessing\spawn.py", line 115, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input
as add on info: (GerVoice3.7) E:\DeepFakes\cleanRTVC>conda list torch Name Version Build Channel pytorch 1.2.0 py3.7_cuda100_cudnn7_1 pytorch torchfile 0.1.0 pypi_0 pypi torchvision 0.4.0 py37_cu100 pytorch
any hint of what could go wrong here? cant point out an error?