Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
4,047 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

4047 Commits

Author SHA1 Message Date
Eren Gölge b6073d16fb Return duration by ForwardTTS inference 2022-04-19 11:00:15 +02:00
Eren Gölge 7ce4444056 Make style 2022-04-19 10:59:59 +02:00
Eren Gölge df30f9d885 Update ForwardTTSe2e tests 2022-04-19 10:58:52 +02:00
Eren Gölge 8f3552fbaa Remove redundant abstract function 2022-04-19 09:23:35 +02:00
Eren Gölge 5cd7fa6228 Refactor TTSDataset to use numpy transforms 2022-04-19 09:23:18 +02:00
Eren Gölge 3824838e5d Update ForwardTTSE2eLoss 2022-04-19 09:22:50 +02:00
Eren Gölge 85c03c75ca Make AP optional in BaseTTS 2022-04-19 09:22:08 +02:00
Eren Gölge 2457739b5e Add numpy and torch transforms 2022-04-19 09:21:46 +02:00
Eren Gölge 7742c0b64e Refactor ForwardTTS to skip decoder 2022-04-19 09:21:31 +02:00
Eren Gölge 518b216631 Make plot results more general 2022-04-19 09:20:31 +02:00
Eren Gölge 82c2ca505d Add missing kernel size attr to transformer layer 2022-04-19 09:19:57 +02:00
Eren Gölge 622ff07c45 Remove AP from FastPitchE2e 2022-04-19 09:19:07 +02:00
Eren Gölge 52e86d8866 Update fastpitche2e recipe 2022-04-19 09:18:49 +02:00
Eren Gölge 519ee7c776 Update import statements 2022-04-19 09:16:03 +02:00
Eren Gölge ad24598797 Remove redundancy 2022-04-04 09:46:30 +02:00
Eren Gölge 9e456e8053 Fix Vocoder logging 2022-04-04 09:46:10 +02:00
Eren Gölge e5a9902e85 Rename vars in VITS 2022-04-04 09:45:46 +02:00
Eren Gölge 8f21991a84 Add cond layer in decoder 2022-04-04 09:44:20 +02:00
Eren Gölge 8408b983b2 Refactor multi-speaker init in ForwardTTS 2022-04-04 09:43:46 +02:00
Eren Gölge f1b034c8b0 Implement BaseTTSE2E 2022-04-04 09:43:15 +02:00
Eren Gölge 29216ff907 Implement ForwardTTSE2E Loss 2022-04-04 09:42:50 +02:00
Eren Gölge 95b52a65af Implement FastPitchE2E LJSpeech recipe 2022-04-04 09:41:46 +02:00
Eren Gölge 2c0cd0ddd5 Implement ForwardTTSE2E tests 2022-04-04 09:41:25 +02:00
Eren Gölge ade84aa124 Implement FastPitchE2EConfig 2022-04-04 09:41:05 +02:00
Eren Gölge c369f087ab Implement ForwardTTSE2Eg 2022-04-04 09:40:36 +02:00
Eren Gölge 1c3623af33
Fix model manager (#1436) 
* Fix manager

* Make style
 2022-03-23 12:57:14 +01:00
Eren Gölge 72d85e53c9
Update model file extension (#1422) 
* Update model file ext to ```.pth```

* Update docs

* Rename more

* Find model files
 2022-03-22 17:55:00 +01:00
Edresson Casanova ccdc2300dc
Add eval_split and eval_split_size in the call of load_tts_samples for all recipes (#1424) 2022-03-22 12:54:41 +01:00
Eren Gölge 2e6e8f651d
Update CheckSpectrograms notebook (#1418) 2022-03-18 16:48:24 +01:00
Eren Gölge c7f9ec07c8
Hinge Gruut version to 2.2.3 (#1419) 2022-03-18 16:47:50 +01:00
Eren Gölge fd56fabb21
Fix #1380 (#1409) 2022-03-16 12:38:27 +01:00
Eren Gölge 0870a4faa2
Make style (#1405) 2022-03-16 12:13:55 +01:00
WeberJulian 690c96ed28
Fix default phonemizer for ja and zh (#1399) 2022-03-16 12:13:22 +01:00
Eren Gölge f40b833659
Add CITATION.cff (#1404) 2022-03-16 12:05:17 +01:00
WeberJulian 24b57f6a0e
Fix typo workflow text (#1403) 2022-03-16 11:51:37 +01:00
Edresson Casanova f81892483d
REBASED: Transform Speaker Encoder in a Generic Encoder and Implement Emotion Encoder training support (#1349) 
* Rename Speaker encoder module to encoder

* Add a generic emotion dataset formatter

* Transform the Speaker Encoder dataset to a generic dataset and create emotion encoder config

* Add class map in emotion config

* Add Base encoder config

* Add evaluation encoder script

* Fix the bug in plot_embeddings

* Enable Weight decay for encoder training

* Add argumnet to disable storage

* Add Perfect Sampler and remove storage

* Add evaluation during encoder training

* Fix lint checks

* Remove useless config parameter

* Active evaluation in speaker encoder test and use multispeaker dataset for this test

* Unit tests fixs

* Remove useless tests for speedup the aux_tests

* Use get_optimizer in Encoder

* Add BaseEncoder Class

* Fix the unitests

* Add Perfect Batch Sampler unit test

* Add compute encoder accuracy in a function
 2022-03-11 14:43:40 +01:00
Edresson Casanova 36e9ea2f97
Open bible dataset formatter (#1365) 
* Add support for voice conversion inference

* Cache d_vectors_by_speaker for fast inference using a bigger speakers.json

* Rebase bug fix

* Use the average d-vector for inference

* Fix the bug in find unique chars script

* Add OpenBible formatter

Co-authored-by: Eren Gölge <erogol@hotmail.com>
 2022-03-11 10:43:31 +01:00
Eren Gölge b0be825d92
Update issue template (#1370) 
* Add bug_report template

* Fix typos
 2022-03-11 10:40:20 +01:00
Edresson Casanova dbe9da7f15
Add Voice conversion inference support (#1337) 
* Add support for voice conversion inference

* Cache d_vectors_by_speaker for fast inference using a bigger speakers.json

* Rebase bug fix

* Use the average d-vector for inference
 2022-03-10 14:57:12 +01:00
Edresson Casanova 917f417ac4
Add alphas to control language and speaker balancer (#1216) 
* Add alphas to control language and speaker balancer

* Add docs for speaker and language samplers

* Change the Samplers weights to float for save memory

* Change the test_samplers to unittest format

* Add get_sampler method in BaseTTS

* Fix rebase issues

* Add language and speaker samplers support for DDP training

* Rename distributed sampler wrapper

* Remove the DistributedSamplerWrapper and use the one from Trainer

* Bugfix after rebase

* Move the samplers config to tts config
 2022-03-10 14:56:09 +01:00
Edresson Casanova f381e29b91
REBASED: Add support for the speaker encoder training using torch spectrograms (#1348) 
* Add support for the speaker encoder training using torch spectrograms

* Remove useless function in speaker encoder dataset class
 2022-03-10 14:54:51 +01:00
Eren Gölge 07d96f7991 Fix DocQA title 2022-03-10 12:17:06 +01:00
Yanlong Wang 8a007c8834
feat: add docsqa to docs website (#1363) 2022-03-10 11:40:06 +01:00
Eren Gölge 48f6bb405a
Fix recipes as to the recent API changes. (#1367) 
* Fix recipes -> #1366

* Fix trainer docs
 2022-03-10 11:36:38 +01:00
Edresson Casanova d792b78703
Fix multilingual recipe (#1354) 2022-03-09 16:18:17 +01:00
Eren Gölge c670365507 Fix VCTK recipe and formatter 2022-03-08 14:20:34 +01:00
Eren Gölge 0cf3265a46
Merge pull request #1347 from coqui-ai/dev 
v0.6.1
 2022-03-07 16:02:19 +01:00
Eren Gölge 8feb41d361 Bump up to v0.6.1 2022-03-07 15:57:44 +01:00
Eren Gölge 6df69f79ea Revert DocQA as it fails on readthedocs 2022-03-07 15:54:43 +01:00
Eren Gölge 95e551dd0a Update requirements.txt for coqui-trainer 2022-03-07 14:31:25 +01:00