Eren Gölge
|
5b70c8ba4f
|
enable backward compat for loading the best model
|
2021-02-18 17:20:36 +00:00 |
Eren Gölge
|
e4f81d6856
|
Merge pull request #654 from kirianguiller/chinese-implementation
Chinese implementation (merge into dev)
|
2021-02-18 17:15:32 +01:00 |
kirianguiller
|
35a781d5af
|
Merge branch 'chinese-implementation' of https://github.com/kirianguiller/TTS into chinese-implementation
|
2021-02-17 21:02:44 +01:00 |
kirianguiller
|
22a6bbfa80
|
remove gst handling in synthetizer.py class
|
2021-02-17 20:53:56 +01:00 |
kirianguiller
|
184ce07718
|
add pypinyin and jieba to requierements.txt (chinese implementation)
|
2021-02-17 20:53:56 +01:00 |
kirianguiller
|
3911b87e54
|
remove re.Match typing in '_number_replace()'
|
2021-02-17 20:53:56 +01:00 |
kirianguiller
|
fb0655d1e7
|
modify according to PR reviews
|
2021-02-17 20:53:56 +01:00 |
kirianguiller
|
c4c7bc1b88
|
<add> Chinese mandarin implementation (tacotron2)
|
2021-02-17 20:53:56 +01:00 |
Eren Gölge
|
d0454461de
|
Merge branch 'pr/gerazov/650-2' into dev
|
2021-02-17 13:40:45 +00:00 |
Eren Gölge
|
a8ea0ea6ce
|
Docstrings for audioprocessor
|
2021-02-17 13:35:41 +00:00 |
Eren Gölge
|
f6e6314910
|
add RUSLAN dataset preprocessor
|
2021-02-17 13:35:23 +00:00 |
Eren Gölge
|
ce0c5eccbd
|
do not test server and modelManager until fixing #657
|
2021-02-17 00:35:43 +00:00 |
kirianguiller
|
4543562467
|
remove gst handling in synthetizer.py class
|
2021-02-16 20:23:02 +01:00 |
kirianguiller
|
fe049cb480
|
add pypinyin and jieba to requierements.txt (chinese implementation)
|
2021-02-16 18:05:40 +01:00 |
kirianguiller
|
a9ea71c601
|
remove re.Match typing in '_number_replace()'
|
2021-02-16 17:41:06 +01:00 |
kirianguiller
|
3e59d3c28d
|
modify according to PR reviews
|
2021-02-16 17:25:18 +01:00 |
gerazov
|
61c88beb94
|
refactored keep_all_best
|
2021-02-15 18:40:17 +01:00 |
Eren Gölge
|
eb543c027e
|
Merge branch 'dev' of https://github.com/mozilla/TTS into dev
|
2021-02-15 17:06:40 +00:00 |
Eren Gölge
|
8a106e0527
|
fix #655
|
2021-02-15 17:06:03 +00:00 |
kirianguiller
|
9cb02aeea7
|
<add> Chinese mandarin implementation (tacotron2)
|
2021-02-15 16:16:05 +01:00 |
Adonis Pujols
|
40f4475723
|
add encoding="utf-8"
|
2021-02-15 16:15:49 +01:00 |
Eren Gölge
|
216945e653
|
Merge pull request #647 from adonispujols/patch-1
Easy Fix for #454 (which was somehow deleted?)
|
2021-02-15 13:17:17 +01:00 |
Eren Gölge
|
06a3ba2fe2
|
linter update
|
2021-02-15 12:10:19 +00:00 |
Eren Gölge
|
7f58fa365b
|
Merge branch 'save_characters' into dev
|
2021-02-15 12:07:28 +00:00 |
Eren Gölge
|
ff218e2370
|
remove redundancy
|
2021-02-15 12:07:02 +00:00 |
Eren Gölge
|
80af8ca5e1
|
Update TTS/utils/arguments.py
Co-authored-by: Jörg Thalheim <Mic92@users.noreply.github.com>
|
2021-02-15 13:03:59 +01:00 |
Eren Gölge
|
3b6ce04332
|
Update TTS/bin/find_unique_chars.py
Co-authored-by: Jörg Thalheim <Mic92@users.noreply.github.com>
|
2021-02-15 13:02:29 +01:00 |
Eren Gölge
|
706e8410cd
|
linterup date
|
2021-02-15 11:42:51 +00:00 |
Eren Gölge
|
dc3596dad4
|
model_manager tests
|
2021-02-15 11:29:22 +00:00 |
Eren Gölge
|
77e630348e
|
author , license and contact info in .model.json
|
2021-02-15 11:02:21 +00:00 |
Eren Gölge
|
e1bc823e44
|
Merge branch 'pr/nmstoker/652' into dev
|
2021-02-15 10:57:12 +00:00 |
nmstoker
|
33bcdc6ff8
|
Updating models list to include EK1 TTS/vocoder
|
2021-02-14 23:44:05 +00:00 |
Eren Gölge
|
c613e0142f
|
update ci to espeak-ng
|
2021-02-12 14:55:08 +00:00 |
Eren Gölge
|
420901f4c2
|
linter fixes
|
2021-02-12 14:41:17 +00:00 |
Eren Gölge
|
4244096ccb
|
update test_text_processing for espeak-ng
|
2021-02-12 14:07:26 +00:00 |
Eren Gölge
|
b28c724c04
|
remove _phoneme_punctuations
|
2021-02-12 12:10:57 +00:00 |
Eren Gölge
|
7ab527d17e
|
save default model chars to the training config file
|
2021-02-12 12:06:46 +00:00 |
Eren Gölge
|
593cedee14
|
parse_characters function
|
2021-02-12 12:05:56 +00:00 |
Eren Gölge
|
2abfff17f9
|
enable saving model characters in io.py
|
2021-02-12 12:04:41 +00:00 |
Eren Gölge
|
918f007a11
|
docstring update
|
2021-02-12 12:04:07 +00:00 |
Eren Gölge
|
e774f68aee
|
save used model characters to the checkpoints
|
2021-02-12 12:03:42 +00:00 |
Eren Gölge
|
e9e07844b7
|
Update README.md
Update contribution guidelines
|
2021-02-12 11:36:31 +01:00 |
gerazov
|
0e78e31dbf
|
reformated docstrings in arguments.py
|
2021-02-12 11:36:01 +01:00 |
gerazov
|
702dff3edc
|
added keep_best and keep_after to test configs.
|
2021-02-12 11:03:52 +01:00 |
gerazov
|
310d18325e
|
brushed up printing model load path and best loss path
|
2021-02-12 10:55:45 +01:00 |
Eren Gölge
|
8b6fd76ad2
|
find unique characters in a dataset
|
2021-02-12 09:46:11 +00:00 |
gerazov
|
af46727517
|
loading last checkpoint/best_model works, deleting last best models options added, loading last best_loss added
|
2021-02-12 02:12:00 +01:00 |
Eren Gölge
|
a1e595790d
|
use default vocoders in server.pu
|
2021-02-11 15:31:39 +00:00 |
Eren Gölge
|
8aa6a0decb
|
set an output_sample_rate in synthesizer and use it for writing the wav
file
|
2021-02-11 15:28:07 +00:00 |
Eren Gölge
|
0c52d27d65
|
return the json entry of the downloaded model
|
2021-02-11 15:27:41 +00:00 |