Commit Graph

  • 7bb45a20ec Build and publish CPU only Docker image Reuben Morais 2022-05-11 14:41:07 +02:00
  • 27cf388a79 Update CI tests (#1572) Eren Gölge 2022-05-12 18:41:01 +02:00
  • 4857967063 🐍 Python 3.10.x support and drop Python 3.6 support (#1565) Eren Gölge 2022-05-12 15:50:25 +02:00
  • a97eed696a Fix the bug in eSpeak wrapper for eSpeak version 1.48.15 (#1560) Edresson Casanova 2022-05-12 10:15:18 -03:00
  • e45ae57aef Merge pull request #1550 from coqui-ai/fix-upsampling-asserts Eren Gölge 2022-05-12 14:51:41 +02:00
  • 175ca06388 Add reinit text encoder and duration predictor parameter (#1562) Edresson Casanova 2022-05-09 14:28:37 -03:00
  • 182711043c Fix the VITS upsampling asserts Edresson Casanova 2022-05-07 14:13:05 -03:00
  • f9d91a55f2 Improve data_path resolvement (#1567) Taras Sereda 2022-05-12 14:10:35 +03:00
  • d5d590bc36 Fix Dockerfile Eren Gölge 2022-05-12 12:55:27 +02:00
  • 6484be687c Build and publish CPU only Docker image Reuben Morais 2022-05-11 14:41:07 +02:00
  • 2fc38f67d2 Update SpeakerManager init in Synthesizer Eren Gölge 2022-05-11 11:32:27 +02:00
  • c3f8c4d5eb Return default SpeakerManager if no d_vector_file Eren Gölge 2022-05-11 11:31:45 +02:00
  • 121e9ed685 Pass use_cuda to init_encoder Eren Gölge 2022-05-11 11:31:17 +02:00
  • c18bd21b3f Return durations at VITS inference Eren Gölge 2022-05-11 11:30:05 +02:00
  • 5021a03de0 Use torch.no_grad for VITS inference Eren Gölge 2022-05-11 11:29:36 +02:00
  • 3f03e3012c Fix batch_group_size in VITS Eren Gölge 2022-05-07 13:40:34 +02:00
  • fa887ef5f9 Fix issue probably-meant-fstring found at https://codereview.doctor (#1532) code-review-doctor 2022-05-07 12:33:40 +01:00
  • a34076af35 Update documentation for multi-gpu training Arvind Suresh 2022-05-03 08:01:10 -04:00
  • a0a9279e4b Fix GAN optimizer order Eren Gölge 2022-05-07 13:28:22 +02:00
  • 60034674f9 Remove audio padding before mel spec extraction Edresson Casanova 2022-04-28 15:40:16 -03:00
  • fbdf76b2fc returns y_mask in VITS inference (#1540) WeberJulian 2022-04-27 10:42:26 +02:00
  • 5680b599ca Fix style fix-asserts+mas Edresson Casanova 2022-05-02 15:51:42 -03:00
  • 39db650bdb Fix the VITS upsampling asserts Edresson Casanova 2022-05-02 15:43:23 -03:00
  • 2f39054557 Fix unit test Edresson Casanova 2022-04-29 16:29:44 -03:00
  • 4693d87974 Fix style Edresson Casanova 2022-04-29 07:28:39 -03:00
  • 9fa014ce34 Change order of HIFI-GAN optimizers to be equal than the original repository Edresson Casanova 2022-04-28 17:08:04 -03:00
  • 1ff925d558 Remove audio padding before mel spec extraction Edresson Casanova 2022-04-28 15:40:16 -03:00
  • b78431d7e2 Fix MAS Eren Gölge 2022-05-03 00:34:55 +02:00
  • 76b274e690 Merge pull request #1541 from coqui-ai/comp_emb_fix Edresson Casanova 2022-04-27 07:28:48 -03:00
  • 379ccd7ba6 returns y_mask in VITS inference (#1540) WeberJulian 2022-04-27 10:42:26 +02:00
  • 6233f4fcd7 Bug fix in compute embedding without eval partition Edresson Casanova 2022-04-26 13:54:09 -03:00
  • a41e860a66 Update Coqpit requirement (#1539) Edresson Casanova 2022-04-26 12:39:36 -03:00
  • 69c8d0b7c9 Update Coqpit requirement update-coqpit-req Edresson Casanova 2022-04-26 09:30:18 -03:00
  • c50a427b51 Update Coqpit requeriment VITS-upsample Edresson Casanova 2022-04-26 09:22:39 -03:00
  • 8d228ab22a Trick to Upsampling to High sampling rates using VITS model (#1456) Edresson Casanova 2022-04-26 06:47:46 -03:00
  • af98ec8eb9 Move upsampling tests to test_vits.py Edresson Casanova 2022-04-25 09:06:40 -03:00
  • f4e53295b1 Add asserts for encoder_sample_rate part Edresson Casanova 2022-04-22 12:07:37 -03:00
  • ce7138d9d4 Add upsampling_init and upsampling_z methods Edresson Casanova 2022-04-22 09:03:31 -03:00
  • b3e2c58398 Rename TTS_part_sample_rate to encoder_sample_rate Edresson Casanova 2022-04-22 07:57:27 -03:00
  • 3f3efe88bb Fix the docs Edresson Casanova 2022-04-22 07:49:51 -03:00
  • d495e4581f Add docs for VITS upsampling Edresson Casanova 2022-04-21 16:57:36 -03:00
  • 1e75942dbc Remove useless detach_z_vocoder parameter Edresson Casanova 2022-04-21 15:59:34 -03:00
  • 984e2d66ac Add unit tests Edresson Casanova 2022-04-21 15:57:43 -03:00
  • c32082a62c Bug fix in speaker encoder load in inference time Edresson Casanova 2022-04-21 15:55:49 -03:00
  • adcc2f8299 Add the period for VITS multi-period discriminator in model_args Edresson Casanova 2022-04-21 10:03:37 -03:00
  • 9252b3c5bd Style fix Edresson Casanova 2022-04-21 09:03:03 -03:00
  • 17b6486ef1 Add RMS based norm in save_wav method Edresson Casanova 2022-04-21 08:26:27 -03:00
  • 18d110eb23 Fix lint checks Edresson Casanova 2022-03-28 22:04:49 +00:00
  • faec6393bc Fix the bug in inference Edresson Casanova 2022-03-28 20:01:51 +00:00
  • 99ecf357af Add upsample VITS support Edresson Casanova 2022-03-24 15:10:02 -03:00
  • 4d1718a19a Implement get_state_dict update_model_save Eren Gölge 2022-04-22 12:39:46 +02:00
  • dfc19cd3ae Remove remaned trainer functions Eren Gölge 2022-04-22 12:37:35 +02:00
  • 21cbfe964e Add RMS based norm in save_wav method VITS-debug-dp Edresson Casanova 2022-04-21 08:26:27 -03:00
  • c410bc58ef Bump to v0.6.2 v0.6.2 Eren Gölge 2022-04-20 11:46:26 +02:00
  • 5271846d9c Add Speech style balancer Edresson Casanova 2022-04-19 15:51:15 -03:00
  • 30bea7d53c Update manage.py (#1514) WeberJulian 2022-04-19 14:27:32 +02:00
  • b45d5c5c60 Improve docsQA default questions (#1411) Yanlong Wang 2022-04-19 20:24:34 +08:00
  • 7b6339f2ed Update manage.py patch-print-license WeberJulian 2022-04-19 14:23:36 +02:00
  • a050aa7bb7 Update manage.py print_license_info WeberJulian 2022-04-19 14:18:52 +02:00
  • 7133f8f47d Print Model's license when downloading (#1512) Eren Gölge 2022-04-19 14:18:49 +02:00
  • 4953636b14 Add African models (#1511) WeberJulian 2022-04-19 14:18:30 +02:00
  • 816d375ae3 Make style Eren Gölge 2022-04-19 14:10:52 +02:00
  • 07a56641f1 Add a new license link Eren Gölge 2022-04-19 13:59:38 +02:00
  • da52a45fca Make style Eren Gölge 2022-04-19 13:57:14 +02:00
  • 5cc8e48c3a Print model license while downloading Eren Gölge 2022-04-19 11:26:02 +02:00
  • b6073d16fb Return duration by ForwardTTS inference Eren Gölge 2022-04-19 11:00:15 +02:00
  • 7ce4444056 Make style Eren Gölge 2022-04-19 10:59:59 +02:00
  • df30f9d885 Update ForwardTTSe2e tests Eren Gölge 2022-04-19 10:58:52 +02:00
  • 8f3552fbaa Remove redundant abstract function Eren Gölge 2022-04-19 09:23:35 +02:00
  • 5cd7fa6228 Refactor TTSDataset to use numpy transforms Eren Gölge 2022-04-19 09:23:18 +02:00
  • 3824838e5d Update ForwardTTSE2eLoss Eren Gölge 2022-04-19 09:22:50 +02:00
  • 85c03c75ca Make AP optional in BaseTTS Eren Gölge 2022-04-19 09:22:08 +02:00
  • 2457739b5e Add numpy and torch transforms Eren Gölge 2022-04-19 09:21:46 +02:00
  • 7742c0b64e Refactor ForwardTTS to skip decoder Eren Gölge 2022-04-19 09:21:31 +02:00
  • 518b216631 Make plot results more general Eren Gölge 2022-04-19 09:20:31 +02:00
  • 82c2ca505d Add missing kernel size attr to transformer layer Eren Gölge 2022-04-19 09:19:57 +02:00
  • 622ff07c45 Remove AP from FastPitchE2e Eren Gölge 2022-04-19 09:19:07 +02:00
  • 52e86d8866 Update fastpitche2e recipe Eren Gölge 2022-04-19 09:18:49 +02:00
  • 519ee7c776 Update import statements Eren Gölge 2022-04-19 09:16:03 +02:00
  • 093bd07528 Add reversal classifier loss Edresson Casanova 2022-04-18 21:09:59 -03:00
  • 8a3396d9c1 Add prosody encoder training support Edresson Casanova 2022-04-18 17:01:44 -03:00
  • e8573bfe3e Update CONTRIBUTING.md (#1463) v0.6.2_models jackiexiao 2022-04-15 20:43:46 +08:00
  • c18100d112 Merge branch 'docker-ci' into dev (Fixes #1498) Reuben Morais 2022-04-15 02:32:51 +02:00
  • 27fcb5dabf Add Dockerfile and build/push CI Reuben Morais 2022-04-15 01:13:32 +02:00
  • bb7a645e7a Add debug script Edresson Casanova 2022-04-14 08:31:52 -03:00
  • 164c7dd676 Update requirements coqui_trainer -> trainer (#1478) Eren Gölge 2022-04-08 14:47:09 +02:00
  • 3abe75c1d3 Update requirements coqui_trainer -> trainer update_trainer Eren Gölge 2022-04-07 14:37:55 +02:00
  • ad24598797 Remove redundancy Eren Gölge 2022-04-04 09:46:30 +02:00
  • 9e456e8053 Fix Vocoder logging Eren Gölge 2022-04-04 09:46:10 +02:00
  • e5a9902e85 Rename vars in VITS Eren Gölge 2022-04-04 09:45:46 +02:00
  • 8f21991a84 Add cond layer in decoder Eren Gölge 2022-04-04 09:44:20 +02:00
  • 8408b983b2 Refactor multi-speaker init in ForwardTTS Eren Gölge 2022-04-04 09:43:46 +02:00
  • f1b034c8b0 Implement BaseTTSE2E Eren Gölge 2022-04-04 09:43:15 +02:00
  • 29216ff907 Implement ForwardTTSE2E Loss Eren Gölge 2022-04-04 09:42:50 +02:00
  • 95b52a65af Implement FastPitchE2E LJSpeech recipe Eren Gölge 2022-04-04 09:41:46 +02:00
  • 2c0cd0ddd5 Implement ForwardTTSE2E tests Eren Gölge 2022-04-04 09:41:25 +02:00
  • ade84aa124 Implement FastPitchE2EConfig Eren Gölge 2022-04-04 09:41:05 +02:00
  • c369f087ab Implement ForwardTTSE2Eg Eren Gölge 2022-04-04 09:40:36 +02:00
  • f31ba25233 Add emotion embedding in the encoder Edresson Casanova 2022-03-31 19:14:41 -03:00
  • 314f95f974 Add formatter for the Emotional Speech Dataset Edresson Casanova 2022-03-31 17:27:30 +00:00