Issues
- 0
[CONTRIBUTION] Speech Dataset Generator
#136 opened by davidmartinrius - 1
Transcript.csv file?
#131 opened by Hashirkhan1996 - 0
Tensorflow error
#135 opened by Deepjoy-Dey - 1
- 4
Getting around: raise ValueError("Can't load save_path when it is None.") ?
#112 opened by CoderReece - 1
I've uploaded Donald Trump speeches and transcripts
#123 opened by eyast - 8
Generated wave were empty
#122 opened by frozen-finger - 0
- 0
- 1
- 1
IOError: [Errno 2] No such file or directory: '/data/private/voice/LJSpeech-1.0/transcript.csv'
#130 opened by Waguitar - 1
about train.py "line 101 while 1 "
#106 opened by sunnnnnnnny - 3
Formatting Custom Training Data & ValueError: bucket_boundaries must not be empty
#113 opened by dbarroso1 - 7
Other language
#94 opened by skyepodium - 0
IOError: [Errno 2] No such file or directory: '/data/private/voice/LJSpeech-1.0/transcript.csv'
#129 opened by Waguitar - 0
Get MelSpectogram for wavenet
#128 opened by Imtinan1996 - 1
Segmentation fault on training
#127 opened by nicolagambini - 0
Error in data_load.py---TypeError: a bytes-like object is required, not 'str'
#126 opened by mingze-sheep - 5
possibly training without transcripts
#100 opened by DonaldTsang - 0
How can we exploit forced alignments?
#125 opened by yoosif0 - 0
error in utils,py
#124 opened by mukul166 - 6
Bus error: 10 at training
#117 opened by kouohhashi - 0
- 0
About the performance of synthesis
#119 opened by CherryCloris - 0
- 0
How to synthesize long sentences?
#118 opened by hadiasheri - 2
File not found even when i gave the path correctly in the hyper_params file...
#102 opened by DhanushDK17 - 2
training from audiobook
#104 opened by pragmascript - 1
How long should I wait for the result generated after I perform the train.py?
#115 opened by juihsuanlee - 6
Pre-trained model sharing?
#107 opened by dreamibor - 0
How to play the generated audio file
#111 opened by erammunawwar - 0
- 0
- 4
No such file or directory: 'WEB/text.csv'
#90 opened by iamcaochong - 0
Conditioning
#108 opened by ronny3050 - 11
OOM out of memory when training step.
#101 opened by luocanrao - 0
Error decoder1 using uninitialized value
#105 opened by youngsuenXMLY - 0
Hyperparameter estimation
#103 opened by ErfolgreichCharismatisch - 0
- 0
I am a beginner, not find the audio data and its text from your dropbox,coule you tell me how to do it?
#98 opened by sunnnnnnnny - 0
[question] Is it possible to use data like this?
#97 opened by rraallvv - 2
- 0
Exception when calling bidirectional_dynamic_rnn, ValueError: None values not supported.
#95 opened by Shirley-Ji - 1
Another problem
#89 opened by GGLW123 - 0
mean_loss1 & mean_loss2 meaning
#93 opened by eazhary - 1
sanity_check = False crashes training
#91 opened by aijanai - 0
Great implementation, thanks!
#92 opened by aijanai - 0
Having problem with batch number
#88 opened by GGLW123 - 0
Hello, I have a confusion on the decoder. Is the former output of Decoder RNN transferred to the input of next timestep, that is the input of next Pre-net, as is shonw in Fig.1 in the paper?
#86 opened by Taishanren80 - 1
Is possible test for spanish?
#85 opened by johnfelipe