coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,865 Commits
80 Branches
98 Tags
316 MiB
Commit Graph

1865 Commits (d6bd3cd8b8981add60fa727dd6385b2f1d99822a)

Author SHA1 Message Date
erogol c008003506 do not check sample rate as loading stats file for normalization to enable interpolation for different sample rate vocoder 2020-09-18 12:52:19 +02:00
mueller 6b0621c794 cleanup 2020-09-17 16:46:43 +02:00
mueller a273b1a210 add: add random noise to dataset 2020-09-17 14:23:40 +02:00
mueller e36a3067e4 add: save wavs instead feats to storage. 
This is done in order to mitigate staleness when caching and loading from data storage
 2020-09-17 14:14:30 +02:00
mueller 1511076fde add: Configurable encoder dataset storage to reduce disk I/O 
add: Averaged time for data loader to console and Tensorboard output
 2020-09-17 12:29:38 +02:00
erogol 3660c57f1e time seperable convolution encoder, huber loss for duration predictor 2020-09-17 03:10:58 +02:00
mueller 95d2906307 add: Mozilla Commonvoice, VoxCeleb1+2, LibriTTS to Speaker Encoder Training 2020-09-16 16:49:53 +02:00
mueller c909ca3855 Improve runtime of __parse_items() from O(|speakers|*|items|) to O(|items|) 2020-09-16 15:55:55 +02:00
mueller d733b90255 Improve runtime of __parse_items() from O(|speakers|*|items|) to O(|items|) 2020-09-16 15:09:02 +02:00
Eren Gölge e732db76f1
Merge pull request #513 from maxbachmann/master 
use difflib for string matching
 2020-09-15 10:24:01 +02:00
maxbachmann 60ce862113
use difflib for string matching 2020-09-14 23:55:34 +02:00
erogol f1a75468c2 fix arguments 2020-09-12 04:00:25 +02:00
erogol 7c2c4d6f27 pass x_mask to layer norm 2020-09-12 03:41:37 +02:00
erogol 53523eebbe layer norm before GLU 2020-09-12 03:41:37 +02:00
erogol 45fbc0d003 convolution encoder with GLU and res connections 2020-09-12 03:40:21 +02:00
erogol 498a3ea36f fix condition check 2020-09-12 03:39:01 +02:00
erogol 72b8ac0ff6 remove redundant arguments 2020-09-12 03:37:47 +02:00
erogol 15e6ab3912 glow-tts module renaming updates 2020-09-12 03:33:36 +02:00
erogol 0ffe91b21d remove breakpoint() 2020-09-11 19:01:38 +02:00
erogol 1c1984d25b comments update 2020-09-11 19:01:38 +02:00
erogol a012537908 remove breakpoint 2020-09-11 19:01:38 +02:00
erogol 1b238f04b2 add gated conv encoder to glow-tts 2020-09-11 19:01:38 +02:00
erogol 14356d3250 glow-tts with relative pos encoding 2020-09-11 19:01:38 +02:00
erogol 09ad6a09b0 remove debug code 2020-09-11 19:01:38 +02:00
erogol 77c577ddab don't use += 2020-09-11 19:01:38 +02:00
erogol 383c5f7185 add glow-tts model and layers 2020-09-11 19:01:38 +02:00
erogol 43771a3a5c remove redundant arguments 2020-09-11 19:01:38 +02:00
erogol 1dea2c9034 faster sequence masking 2020-09-11 19:01:38 +02:00
erogol 673ba74a80 glow tts training and inference fixes 2020-09-11 19:01:38 +02:00
erogol d5c6d60884 synthesis update for glow tts 2020-09-11 19:01:37 +02:00
erogol 89d15bf118 merge glow-tts after rebranding 2020-09-11 19:01:37 +02:00
erogol 95de34e8ef find cython files insetup 2020-09-11 19:01:07 +02:00
erogol f511521e01 install cython deps 2020-09-11 19:01:07 +02:00
erogol f9001a4bdd refactor and fix compat issues for speaker encoder 2020-09-11 17:17:07 +02:00
erogol 540d811dd5 solve pickling models after module name change 2020-09-11 12:03:39 +02:00
erogol df19428ec6 rename the project to old TTS 2020-09-09 12:27:23 +02:00
erogol daf9c7aaec move notebook 2020-09-07 13:51:14 +02:00
erogol d4319fe42d linter changes and train_tts_test and train_vocoder_test fixes 2020-09-07 13:46:35 +02:00
erogol 3131308baa Merge branch 'dev' 2020-09-07 11:43:26 +02:00
Eren Gölge ee18679e47
Merge pull request #507 from tset-tset-tset/dev 
Add a language_switch='remove-flags' argument when calling phonemize
 2020-09-07 11:18:46 +02:00
tset-tset-tset 4f3917b9a6
Add a language_switch argument when calling phonemize 
The language_switch defaults to keep-flags, but the result is inappropriate.
 2020-09-01 01:15:42 +09:00
erogol 34241815e7 Merge branch 'dev' of https://github.com/mozilla/TTS into dev 2020-08-18 16:44:10 +02:00
erogol 9e33ab9f83 remove redundant arguments of pwgan 2020-08-17 13:56:10 +02:00
Eren Gölge 81dd3629cb
Merge pull request #498 from thllwg/dev 
Missing speaker_mapping argument causes training to break
 2020-08-14 13:07:17 +03:00
Eren Gölge c7c5c0812b
Merge pull request #496 from SanjaESC/patch-2 
Update train_tts.py
 2020-08-14 13:01:57 +03:00
thllwg e07ff8abe8 remove empty space 2020-08-14 11:12:37 +02:00
thllwg c90fce8d8c Fix for #497 2020-08-14 11:11:04 +02:00
Alexander Korolev 2a2a0864c1
Update train_tts.py 
align style_input with the new config key "gst_style_input"
 2020-08-14 09:38:53 +02:00
erogol f35b2ebacd Merge branch 'dev' of https://github.com/mozilla/TTS into dev 2020-08-13 14:46:47 +02:00
Eren Gölge 96815bfdf3
Merge pull request #494 from thllwg/dev 
Fix: Imports in Speaker Encoder
 2020-08-13 14:46:12 +02:00