coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
3,291 Commits
80 Branches
98 Tags
316 MiB
Commit Graph

3291 Commits (c8bbcdfd076183e2b59350e8c274502f4e2935e9)

Author SHA1 Message Date
Edresson 99d40e98d9 fix Lint checks 2021-06-18 14:59:01 -03:00
Edresson 28bec238ca fix Lint checks 2021-06-18 14:33:50 -03:00
Edresson 83644056e3 fix Lint checks 2021-06-18 14:32:28 -03:00
Edresson Casanova e78e3cd81e
Merge branch 'dev' into dev 2021-06-18 14:10:03 -03:00
Edresson b74b510d3c Compute embeddings and find characters using config file 2021-06-18 14:04:49 -03:00
Eren Gölge 79241b69fe
Merge pull request #572 from a-froghyar/fix-extract-tts-script 
Forcing do_trim_silence to False in the extract TTS script
 2021-06-15 10:56:53 +02:00
Eren Gölge 121d5cf5b7
Merge branch 'dev' into fix-extract-tts-script 2021-06-15 10:55:44 +02:00
Eren Gölge d85ee901d5
Fix #571 2021-06-15 10:53:53 +02:00
Adam Froghyar b0aa189348 Forcing do_trim_silence to False in the extract TTS script 2021-06-14 10:44:00 +02:00
Sadam Hussain Memon d0cef713cf
`mixed_precision` set to false 
Change default value of `"mixed_precision" : false` as when it is set true it leads to  `raise RuntimeError(f" [!] NaN loss with {key}.")
RuntimeError:  [!] NaN loss with decoder_loss.`
 2021-06-10 05:51:30 +05:00
Eren Gölge d245b5d48f bump up v0.0.15.1 2021-06-08 09:21:01 +02:00
Eren Gölge d0eb2e636f
Merge pull request #557 from coqui-ai/add-missing-version-file 
add missing VERSION to manifest
 2021-06-08 09:19:29 +02:00
Eren Gölge ed6e109aec add missing VERSION to manifest 2021-06-08 09:17:05 +02:00
Edresson 14b209c7e9 Create a batch for more fast inference on LSTM Speaker Encoder 2021-06-05 03:12:17 -03:00
Eren Gölge b8b79a5e5a fix `use_cuda` bug in `server.py` 2021-06-04 14:02:53 +02:00
Eren Gölge 203ab855c3 bump up to v0.0.15 2021-06-04 13:52:54 +02:00
Eren Gölge 06a7088557
Merge pull request #532 from coqui-ai/auto-pypi-upload 
auto upload to pypi on release
 2021-06-04 13:30:41 +02:00
Eren Gölge ba9bcf7c6b auto upload to pypi on release 2021-06-04 12:20:06 +02:00
Eren Gölge e66753bd0d fixup! new japanese model placeholder in `.models.json` 2021-06-03 18:04:28 +02:00
Eren Gölge bd434636a9 new japanese model placeholder in `.models.json` 2021-06-02 15:54:37 +02:00
Eren Gölge 401fbd8978 bump up to v0.0.15 2021-06-02 11:48:17 +02:00
Eren Gölge db48c69f0f reduce fullband melgan model size for testing 2021-06-02 11:44:53 +02:00
Eren Gölge 4baa59d732 comment `requirements.txt` for japanese deps 2021-06-02 11:44:53 +02:00
Eren Gölge 49c5e5d820 maket style japanese PR 2021-06-02 11:44:46 +02:00
Eren Gölge 0c14278c30 reorg test files 2021-06-02 11:40:26 +02:00
Eren Gölge 73b4083c6c
Merge pull request #502 from kaiidams/kaiidams/kokoro 
Japanese Tacotron 2 model
 2021-06-02 10:20:08 +02:00
Eren Gölge ea31215087
Merge pull request #520 from SanjaESC/patch-1 
fix taco2 speaker-embeddings dimension during inference
 2021-06-02 09:32:24 +02:00
Katsuya Iida 6d8310d2a9 Set the version to the same with the dev branch. 2021-06-02 07:48:28 +09:00
Eren Gölge f53bb9ab1b Merge branch 'replace-unidecode' into dev 2021-06-01 16:09:56 +02:00
Alexander Korolev c1eb9bdcca
fix speaker dim inference 2021-06-01 15:15:26 +02:00
Katsuya Iida 1cc18d1972 Move unittest of Japanese phonemizer. 2021-06-01 18:51:34 +09:00
Alexander Korolev 5b89ef2c6e
fix speaker-embeddings dimension during inference 2021-06-01 11:06:35 +02:00
Eren Gölge d0ab0382fc linter fixes 2021-06-01 09:15:32 +02:00
Eren Gölge 406c4d0577 bump pylint version to 2.8.3 2021-06-01 09:15:15 +02:00
Eren Gölge 4726ae393d pylint disable `not-callable` checks due to the warnings on torch layers 2021-06-01 09:14:16 +02:00
Eren Gölge bec85ac58d make style 2021-05-31 16:37:15 +02:00
Eren Gölge 975531b3f2 update `pylintrc` for torch and numpy functions 2021-05-31 16:11:22 +02:00
Eren Gölge d9f1268f99 init tb_logger None for rank > 0 processes 2021-05-31 15:47:07 +02:00
Eren Gölge 301c516abd Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev 2021-05-31 15:46:25 +02:00
Eren Gölge 92e26b4216
Merge pull request #508 from Edresson/dev 
Implement/Train a better speaker encoder
 2021-05-31 11:45:36 +02:00
Edresson cc192b6843 add resnet speaker encoder train unit test 2021-05-29 22:43:41 -03:00
Edresson 7448177b72 use SpeakerManager on compute embeddings script 2021-05-29 21:11:53 -03:00
Katsuya Iida 2091e808c8 Fix path 2021-05-29 19:41:00 +09:00
Katsuya Iida 88f3255962 Update Kokoro recipe 2021-05-29 19:39:51 +09:00
Katsuya Iida c4a5a73f18 update Kokoro config 2021-05-29 19:17:27 +09:00
Katsuya Iida 29d61741ec Copied recipe 2021-05-29 19:03:23 +09:00
Katsuya Iida 3a9ac2de4a Merge remote-tracking branch 'coqui-ai/main' into kaiidams/kokoro 2021-05-29 09:39:23 +09:00
Katsuya Iida d0c9c1ca5c Move TTS/tts/utils/japanese 2021-05-29 09:21:47 +09:00
Edresson 099142d4dd bug fix 2021-05-27 21:50:56 -03:00
Edresson 208bb0f0ee add batched speaker encoder inference 2021-05-27 20:01:00 -03:00