kirianguiller
|
42ba30eb8f
|
<add> Chinese mandarin implementation (tacotron2)
|
2021-03-08 02:59:24 +01:00 |
|
kirianguiller
|
49665783a6
|
remove gst handling in synthetizer.py class
|
2021-03-08 02:57:11 +01:00 |
|
kirianguiller
|
ab8994e2c6
|
add pypinyin and jieba to requierements.txt (chinese implementation)
|
2021-03-08 02:57:11 +01:00 |
|
kirianguiller
|
e85658ac2b
|
remove re.Match typing in '_number_replace()'
|
2021-03-08 02:57:11 +01:00 |
|
kirianguiller
|
0d4525322c
|
modify according to PR reviews
|
2021-03-08 02:57:11 +01:00 |
|
kirianguiller
|
e6fd118cf8
|
<add> Chinese mandarin implementation (tacotron2)
|
2021-03-08 02:57:11 +01:00 |
|
Eren Gölge
|
e3102e753c
|
enable backward compat for loading the best model
|
2021-03-08 02:57:11 +01:00 |
|
gerazov
|
2451a813a2
|
refactored keep_all_best
|
2021-03-08 02:57:11 +01:00 |
|
gerazov
|
8cefa76bae
|
reformated docstrings in arguments.py
|
2021-03-08 02:57:11 +01:00 |
|
gerazov
|
62147994d4
|
added keep_best and keep_after to test configs.
|
2021-03-08 02:56:36 +01:00 |
|
gerazov
|
2db40457e8
|
brushed up printing model load path and best loss path
|
2021-03-08 02:56:36 +01:00 |
|
gerazov
|
f2e474cd37
|
loading last checkpoint/best_model works, deleting last best models options added, loading last best_loss added
|
2021-03-08 02:56:36 +01:00 |
|
Eren Gölge
|
4111df6769
|
Docstrings for audioprocessor
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
2ca74b8ab3
|
add RUSLAN dataset preprocessor
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
8993120634
|
do not test server and modelManager until fixing #657
|
2021-03-08 02:54:47 +01:00 |
|
Adonis Pujols
|
89b7f01534
|
add encoding="utf-8"
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
ffceccb021
|
fix #655
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
534c341f16
|
linter update
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
0e1e60bef0
|
remove redundancy
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
93a83c0068
|
Update TTS/utils/arguments.py
Co-authored-by: Jörg Thalheim <Mic92@users.noreply.github.com>
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
39fbf2fe84
|
Update TTS/bin/find_unique_chars.py
Co-authored-by: Jörg Thalheim <Mic92@users.noreply.github.com>
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
19e2193c40
|
update ci to espeak-ng
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
ee71eb4eb7
|
linter fixes
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
55fc50b26d
|
update test_text_processing for espeak-ng
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
5b8a6736a7
|
remove _phoneme_punctuations
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
194f82de51
|
save default model chars to the training config file
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
62a8eba3b2
|
parse_characters function
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
0b33acdcca
|
enable saving model characters in io.py
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
f9fe167537
|
docstring update
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
62aeacbdd1
|
save used model characters to the checkpoints
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
8ec28b1ac2
|
linterup date
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
e06c93fe81
|
model_manager tests
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
fe41084eb3
|
author , license and contact info in .model.json
|
2021-03-08 02:54:47 +01:00 |
|
nmstoker
|
ae0d54ddae
|
Updating models list to include EK1 TTS/vocoder
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
c6702b5b9f
|
find unique characters in a dataset
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
dad3565379
|
use default vocoders in server.pu
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
d30608ab17
|
set an output_sample_rate in synthesizer and use it for writing the wav
file
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
3ccb015cd8
|
return the json entry of the downloaded model
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
00e0933f43
|
save_wav with a custom sampling rate
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
9fefc79f0c
|
fix make_symbols
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
8955333e9d
|
use default vocoder in synthesize.py
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
23b282f600
|
define default vocoders
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
6bd8485d10
|
bug fix
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
5f1018abee
|
fix spelling of a def argument and parse phonemes from config.json if
use_phonemes is True
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
1c1abb8a9b
|
docstring update
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
6cd642c2e1
|
add missing phonemes to test_config.json
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
43b951018e
|
fix the default vocoder name
|
2021-03-08 02:54:47 +01:00 |
|
Adonis Pujols
|
81b145c321
|
spelling error. should be multiband not mulitband
|
2021-03-08 02:54:47 +01:00 |
|
Adonis Pujols
|
59b1b13e07
|
spelling error. should be multiband not mulitband
|
2021-03-08 02:54:47 +01:00 |
|
Eren Gölge
|
ee58ff2d38
|
add russian phoneme char
|
2021-03-08 02:54:47 +01:00 |
|