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
4,064 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

1579 Commits

Author SHA1 Message Date
Edresson Casanova bdefc43d96 Bug fix on pre-compute F0 2022-05-19 13:48:02 +00:00
Edresson Casanova d94b8bac02 Add pitch predictor 2022-05-16 21:53:49 +00:00
Edresson Casanova dcd0d1f6a1 Clean up old code 2022-05-16 13:09:12 +00:00
Edresson Casanova 3a524b0597 Add prosody encoder params on config 2022-05-16 09:45:28 -03:00
Edresson Casanova 5271846d9c Add Speech style balancer 2022-04-19 15:51:15 -03:00
Edresson Casanova 093bd07528 Add reversal classifier loss 2022-04-18 21:09:59 -03:00
Edresson Casanova 8a3396d9c1 Add prosody encoder training support 2022-04-18 17:01:44 -03:00
Edresson Casanova f31ba25233 Add emotion embedding in the encoder 2022-03-31 19:14:41 -03:00
Edresson Casanova 314f95f974 Add formatter for the Emotional Speech Dataset 2022-03-31 17:27:30 +00:00
Edresson Casanova 7be9056b3d Remove useless encoder weights reload 2022-03-31 11:05:58 -03:00
Edresson Casanova b692c77e6a Fix emotion unit test 2022-03-31 08:34:08 -03:00
Edresson Casanova 047cebd7b8 Fix Style tests 2022-03-30 16:51:39 -03:00
Edresson Casanova aebbdfc62b
Merge branch 'dev-managers' into dev-emotion 2022-03-30 16:25:47 -03:00
Edresson Casanova 34a92f1b1b Fix the Bug in Synthesizer 2022-03-30 15:32:35 -03:00
Edresson Casanova 397b3e9baf Fix style tests 2022-03-23 15:31:33 -03:00
Edresson Casanova ab20a34170 Fix bug in get_speaker_manager 2022-03-23 15:27:01 -03:00
Edresson Casanova cb941530df Fix docs of set_language_ids_from_config 2022-03-23 15:27:01 -03:00
Edresson Casanova 2bc2685ff9 Add parse_key in set_ids_from_data 2022-03-23 15:27:01 -03:00
Edresson Casanova 88e0cfa5a0 Rename set_embeddings_from_file to load_embeddings_from_file 2022-03-23 15:27:01 -03:00
Edresson Casanova b7eefac47d Rename set_ids_from_file to load_ids_from_file 2022-03-23 15:27:01 -03:00
Edresson Casanova 24274c58f8 Fix unit tests 2022-03-23 15:27:01 -03:00
Edresson Casanova c7af7c6474 Implement LanguageManager inherit BaseIDManager 2022-03-23 15:26:59 -03:00
Edresson Casanova 4fdc864f74 Add EmbeddingManager and BaseIDManager 2022-03-23 15:26:59 -03:00
Edresson Casanova 40df2cfdd1 Change the speaker manager to a generic manager 2022-03-23 15:26:06 -03:00
Eren Gölge 3af01cfe3b
Update base model wrt 👟 (#1406) 2022-03-23 17:24:20 +01:00
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 10dee54ac3 Bug fix in single speaker emotion embedding training 2022-03-16 20:57:14 +00:00
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
Edresson Casanova 38027b15c2 Fix unit tests 2022-03-15 19:40:07 +00:00
Edresson Casanova 4f03784b1f Add emotion external embeddings training unit test 2022-03-15 13:09:58 +00:00
Edresson Casanova 5090034fd1 Add emotion consistency loss 2022-03-15 12:35:00 +00:00
Edresson Casanova cc3821332b Fix the bug in sythesizer 2022-03-15 12:33:36 +00:00
Edresson Casanova e3520e9e9f Add Emotion Support for the VITS model 2022-03-15 01:16:48 +00:00
Edresson Casanova 18d3565d37 Add emotion manager 2022-03-14 14:26:40 +00:00
Edresson Casanova e52b40aca4 Fix bug in get_speaker_manager 2022-03-14 14:15:18 +00:00
Edresson Casanova 8040b930a8 Fix docs of set_language_ids_from_config 2022-03-14 14:14:37 +00:00
Edresson Casanova 0e258d1784 Add parse_key in set_ids_from_data 2022-03-14 13:53:46 +00:00
Edresson Casanova 464775dbaf Rename set_embeddings_from_file to load_embeddings_from_file 2022-03-14 13:34:16 +00:00
Edresson Casanova 7e59755d63 Rename set_ids_from_file to load_ids_from_file 2022-03-14 13:31:01 +00:00
Edresson Casanova 25da4d9b74 Fix unit tests 2022-03-11 19:55:29 -03:00
Edresson Casanova e33819b7de Implement LanguageManager inherit BaseIDManager 2022-03-11 19:25:18 -03:00
Edresson Casanova eac06a5e87 Add EmbeddingManager and BaseIDManager 2022-03-11 19:01:51 -03:00
Edresson Casanova 12e0b6f39e Change the speaker manager to a generic manager 2022-03-11 17:09:58 -03:00
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
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