mozilla
/
TTS
зеркало из https://github.com/mozilla/TTS.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность
1 620 коммитов 13 Ветки 1 Тег 128 MiB
Граф коммитов

1620 Коммитов

Автор SHA1 Сообщение Дата
erogol 1d3c0c8846 raise error if training set is < 100 2020-06-06 13:44:03 +02:00
erogol fedb2542be bug fix vocoder model restore 2020-06-06 13:00:46 +02:00
erogol b86af6538f bug fix for TTS model restore 2020-06-06 12:59:59 +02:00
erogol 79db7d931b bug fix for DDC model eval run 2020-06-05 14:47:25 +02:00
erogol d00b91710a Merge branch 'dev' of https://github.com/mozilla/TTS into dev 2020-06-05 13:28:39 +02:00
erogol 81af469be0 model config update 2020-06-05 13:28:16 +02:00
erogol 72fe5a8217 correct name 2020-06-05 13:27:09 +02:00
erogol c5c3f6094c bug fix for rwd discriminator 2020-06-05 13:25:53 +02:00
erogol 189227c741 bug fix vocoder training 2020-06-05 13:23:11 +02:00
erogol fd8f1ecb7d lint updates 2020-06-04 14:58:18 +02:00
erogol a82f7d129d check DDC parameters in config.json 2020-06-04 14:31:17 +02:00
erogol 66ec1b2e2a setup_model update following TacotronAbstract 2020-06-04 14:30:43 +02:00
erogol 0f88f8ec5a train.py update for DDC 2020-06-04 14:30:12 +02:00
erogol 43d278be2f update model tests for ddc 2020-06-04 14:29:37 +02:00
erogol e272e07ce9 update dummy model config 2020-06-04 14:28:55 +02:00
erogol bd7237d916 inherit TacotronAbstact with both tacotron and tacotron2 2020-06-04 14:28:16 +02:00
erogol b4ac68df7b add DDC loss 2020-06-04 14:27:40 +02:00
erogol 1ca078ae7e update model config.json with double decoder consistency 2020-06-04 14:27:06 +02:00
erogol ef2369e0da update README.md 2020-06-04 14:26:51 +02:00
erogol 1de6825040 tacotron abstract class 2020-06-04 14:26:30 +02:00
erogol 2b361f0b50 visualization fix 2020-06-04 09:51:20 +02:00
erogol ed466c8581 update README.md 2020-06-04 02:58:25 +02:00
erogol be861d7aa0 suppress pylint no-self-use for loss layers 2020-06-03 12:33:53 +02:00
erogol 20a9d51ccc correct loss normalization and function refactoring 2020-06-03 12:16:08 +02:00
erogol 1e017f866a reset loss weights 2020-06-03 12:15:48 +02:00
erogol b25af49c34 espeak install travis 2020-06-02 23:58:18 +02:00
erogol e051dd41b1 Ton of linter fixes 2020-06-02 18:58:10 +02:00
erogol 054c1fce39 travis script for nose 2020-06-02 18:54:29 +02:00
erogol af516aff7f cardboard config update 2020-06-02 18:54:03 +02:00
erogol 808da15e7d update travis script 2020-06-02 17:28:52 +02:00
erogol fd2d0dab41 bug fix 2020-06-02 17:09:05 +02:00
erogol 4619b84ddb multiscale subband stft loss and missing tb_logger for eval stats 2020-06-02 17:07:15 +02:00
erogol 4688ff3528 Merge branch 'dev' of https://github.com/mozilla/TTS into dev 2020-06-01 03:03:17 +02:00
erogol 5662aa3bbe tb eval print 2020-06-01 03:02:51 +02:00
erogol 1a470ba6b9 multiband rwd D config 2020-05-31 19:03:07 +02:00
erogol bb6729b42a add multiband melgan config and rename loss weights for vocoder 2020-05-31 18:56:57 +02:00
erogol 1ec2c497a3 Merge branch 'dev' of https://github.com/mozilla/TTS into dev 2020-05-31 14:18:42 +02:00
erogol 29915ba85c bug fix 2020-05-31 14:18:29 +02:00
Eren Gölge e2dda3377c
Merge pull request #418 from forcecore/fix_phoneme_cache 
Fix phoneme cache file name aliasing problem
 2020-05-31 14:18:04 +02:00
ForceCore 3f78918715 Fix phoneme cache file name aliasing problem 
When the wav file has multiple dots in the file name,
_load_or_generate_phoneme_sequence would only use only the first segment
of the file name and cause overwrite of *_phoneme.npy
 2020-05-31 19:57:08 +09:00
erogol d5bbcd0487 plot fix 2020-05-31 03:31:42 +02:00
erogol 8e7a15f07b version update 2020-05-31 03:31:13 +02:00
erogol d47c9987db initial commit intro. to vocoder submodule 2020-05-30 18:09:25 +02:00
erogol 4ecd47e072 use model_name prefix in tb_logger 2020-05-30 18:08:56 +02:00
erogol 0372c5ce5d set state dict using direct state_dict dict 2020-05-30 18:08:26 +02:00
erogol 5116a20c86 differentiate modules on TB with a prefix 2020-05-30 18:07:01 +02:00
erogol e71a377202 add a non-existing value to avg values 2020-05-30 14:05:19 +02:00
Eren Gölge f3209924f3
Merge pull request #413 from george-roussos/master 
Update compute_statistics.py
 2020-05-25 10:35:46 +02:00
erogol 3eacab9f6a add requirements for speaker encoder 2020-05-25 10:32:42 +02:00
erogol ef7e31c498 fix #412 2020-05-25 10:32:14 +02:00