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
4,568 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

1912 Commits

Author SHA1 Message Date
Edresson 1bd1a0546b Add audio resample in the speaker consistency loss 2021-12-20 11:54:10 +00:00
Edresson 1c6bcda950 Add freeze vocoder generator and flow-based decoder option 2021-12-20 11:54:10 +00:00
WeberJulian 2b952d8b97 freeze vits parts 2021-12-20 11:54:10 +00:00
WeberJulian 005bba60b0 get_speaker_weighted_sampler 2021-12-20 11:54:10 +00:00
Edresson 9de4539422 Update the VITS model docs 2021-12-20 11:54:10 +00:00
Edresson eeb8ac07d9 Add voice conversion fine tuning mode 2021-12-20 11:54:10 +00:00
Edresson 690b37d0ab Add support to use the speaker encoder as loss function in VITS model 2021-12-20 11:54:09 +00:00
Edresson 9b011b1cb3 Add H/ASP original checkpoint support 2021-12-20 11:54:09 +00:00
Edresson 0bdfd3cb50 Add the ValueError in the restore checkpoint exception to avoid problems with the optimizer restauration when new keys are addition 2021-12-20 11:54:09 +00:00
Edresson de78556655 Fix the optimizer parameters bug in multilingual and multispeaker training 2021-12-20 11:54:09 +00:00
Edresson 9be5b75da3 Fix bug after merge 2021-12-20 11:54:09 +00:00
Edresson 76251b619a Fix d-vector multispeaker training bug 2021-12-20 11:54:09 +00:00
Edresson 7ef3ddc6ff Fix unit tests 2021-12-20 11:54:09 +00:00
Edresson 36dcd11453 Fix pylint issues 2021-12-20 11:54:09 +00:00
Edresson c53693c155 Implement vocoder Fine Tuning like SC-GlowTTS paper 2021-12-20 11:54:09 +00:00
Edresson f1f016314e Fix the bug in M-AILABS formatter 2021-12-20 11:54:09 +00:00
Edresson c334d39acc Add voice conversion support for the model VITS trained with external speaker embedding 2021-12-20 11:54:09 +00:00
Edresson e997889ba8 Fix bug in VITS multilingual inference 2021-12-20 11:54:09 +00:00
Edresson 7c0b8ec572 Fix bugs in the non-multilingual VITS inference 2021-12-20 11:54:09 +00:00
Edresson 3fbbebd74d Fix pylint issues 2021-12-20 11:54:09 +00:00
Edresson ac9416fb86 Add multilingual inference support 2021-12-20 11:54:09 +00:00
Edresson dcb2374bc9 Add multilingual training support to the VITS model 2021-12-20 11:54:09 +00:00
Edresson f996afedb0 Implement multilingual dataloader support 2021-12-20 11:54:09 +00:00
Edresson 5f1c18187f Fix pylint issues 2021-12-20 11:54:09 +00:00
Edresson d91c595c5a Implement training support with d_vecs in the VITS model 2021-12-20 11:54:09 +00:00
Edresson 6a7db67a91 Allow ignore speakers for all multispeaker datasets 2021-12-20 11:54:09 +00:00
Edresson e0ad838066 Select randomly a speaker from the speaker manager for the test setences 2021-12-20 11:54:09 +00:00
Edresson eb3e8affe1 Save speakers embeddings/ids before starting training 2021-12-20 11:54:09 +00:00
Eren Gölge 37803467aa
Merge pull request #1021 from loganhart420/dataset_downloaders 
Add addtional datasets
 2021-12-20 10:42:20 +01:00
Reuben Morais 859ac1a54c Include usage instructions in README 2021-12-17 11:37:19 +01:00
loganhart420 103c010eca Add addtional datasets 2021-12-16 07:21:27 -05:00
Jörg Thalheim bce143c738
server: fix compatibility with tts_models/en/ljspeech/fast_pitch (#893) 2021-12-07 14:36:29 +01:00
Eren Gölge babdd84f91 Fix GST inference 
commit d3e477875a7e46a101fcf95a1794442823750fe2
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com>
Date:   Wed Nov 3 10:16:12 2021 +0000

    Read .wav for GST conditioning from CL

commit 074e6d0874d3b34fb6a4991fc17d66dccd413fbb
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com>
Date:   Fri Oct 29 14:43:47 2021 +0100

    Fix GST during inference in Tacotron2

commit fdece14585ab5a36eed1061a9a838d8e48aa6882
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com>
Date:   Wed Nov 3 10:16:12 2021 +0000

    Read .wav for GST conditioning from CL

commit cd29e21b8d0a541ee298d2bf5f67223ad60be38f
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com>
Date:   Fri Oct 29 14:43:47 2021 +0100

    Fix GST during inference in Tacotron2

commit 908ce39370eadcc9fa8510cdb26c9ead87305427
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com>
Date:   Fri Oct 29 12:49:37 2021 +0100

    Make trim_db value negative

commit 1008a2e0f72fa7ca7f0307424f570386f2f16d42
Author: George Rousssos <25833833+george-roussos@users.noreply.github.com>
Date:   Fri Oct 29 12:22:24 2021 +0100

    Set find_endpoint db threshold in config.json
 2021-12-07 13:28:49 +00:00
Eren Gölge ce45d9e1af Make style and lint 2021-12-01 10:42:52 +00:00
Eren Gölge 40cb8ac966 Fix #958 2021-12-01 10:33:34 +00:00
Eren Gölge 512ada7548 Fix callbacks against multi-gpu training 2021-12-01 10:32:14 +00:00
Eren Gölge 2ed9e3c241 Fix constant use of noise augment 2021-11-08 09:20:34 +01:00
Eren Gölge b6b14a76af Fix VITS stochastic duration predictor 2021-11-08 09:20:11 +01:00
Eren Gölge dc3dd55dd9 Add collect_env_info.py 2021-11-08 08:59:08 +01:00
Eren Gölge faafea4cf2 Fix style 2021-11-04 17:04:40 +01:00
Eren Gölge d227aaebcc Print when using Griffin-Lim in Synthesizer 2021-11-01 16:52:26 +01:00
Eren Gölge c5077c6c3f Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev 2021-11-01 16:42:27 +01:00
Eren Gölge 20cebde1c9 Add docstring to MAI labs formatter 2021-11-01 16:41:55 +01:00
Eren Gölge 608f437545 Add a function to find unique chars 2021-11-01 16:41:33 +01:00
Eren Gölge d6d780e758 Fix FastSpeech config 2021-11-01 16:41:15 +01:00
Eren Gölge 5ba47081ee Use GL for VCTK FastPitch models 2021-11-01 16:39:03 +01:00
Michael Hansen 3bc043faeb
Upgrade to gruut 2.0 (#882) 2021-10-31 11:41:55 +01:00
George 37eaefc085
Optional silence trimming during inference and find_endpoint() fix (#898) 
* Set find_endpoint db threshold in config.json

* Optional silence trimming during inference

* Make trim_db value negative
 2021-10-29 18:28:55 +02:00
Eren Gölge 7293abada2 Bump up to v0.4.2 2021-10-29 17:57:30 +02:00
Eren Gölge 2df0752e73
Model zoo tests (#900) 
* Fix VITS model multi-speaker init

* Remove gdrive support in model manager

* Add model zoo tests
 2021-10-29 17:54:16 +02:00
Eren Gölge aaaa591485 Bump up version to v0.4.1 2021-10-26 19:24:17 +02:00
Eren Gölge 3ea1c2037b Fix model entry in .models.json 2021-10-26 19:14:29 +02:00
Eren Gölge fa4ec83c6e Bump up version to v0.4.0 2021-10-26 18:27:39 +02:00
Eren Gölge 035ed432bc
Doc update (#889) 
* Link source files from the docs

* Update glowTTS recipes for docs

* Add dataset downloaders
 2021-10-26 17:41:33 +02:00
Eren Gölge 0cac3f330a Enable custom formatter in load_tts_samples 2021-10-26 13:07:11 +02:00
Eren Gölge 7c10574931 Gateway for TTS models 2021-10-26 13:04:51 +02:00
Eren Gölge 00becf2671 Fix import statements 2021-10-25 19:29:16 +02:00
Eren Gölge 027424dda8 Add VCTK fast_pitch and UK glow-tts 2021-10-25 19:29:16 +02:00
Eren Gölge 70e4d0e524 Fix grad_norm handling 2021-10-21 16:29:06 +00:00
Eren Gölge a409e0f8f8 Update train_tts for multi-speaker 2021-10-21 16:29:06 +00:00
Eren Gölge 2b7d159383 Update BaseTTS for multi-speaker training 2021-10-21 16:29:06 +00:00
Eren Gölge e62d3c5cf7 Use absolute imports for tts configs and models 2021-10-21 16:29:06 +00:00
Eren Gölge 82fed4add2 Make style 2021-10-21 16:05:51 +00:00
Eren Gölge 3cb07fb6b5 Fix SpeakerManager init with data items 2021-10-21 13:54:39 +00:00
Eren Gölge aea90e2501 Comment synthesis.py 2021-10-21 13:53:45 +00:00
Eren Gölge 1987aaaaed Update d-vector reshape in synthesizer 2021-10-21 13:53:25 +00:00
Eren Gölge 3ab009ca8d Edit model configs for multi-speaker 2021-10-21 13:51:37 +00:00
Eren Gölge cea8e1739b Update AlignTTS to use SpeakerManager 2021-10-20 18:22:41 +00:00
Eren Gölge 0e768dd4c5 Update comments 2021-10-20 18:21:26 +00:00
Eren Gölge 7c2cb7cc30 Update BaseTTS 2021-10-20 18:18:22 +00:00
Eren Gölge 330ee7d208 Comment BaseTacotron and remove unused funcs 2021-10-20 18:17:25 +00:00
Eren Gölge aa25f70b95 Update ForwardTTS for multi-speaker 2021-10-20 18:16:41 +00:00
Eren Gölge 0ebc2a400e Implement `_set_speaker_embedding` in GlowTTS 2021-10-20 18:15:20 +00:00
Eren Gölge 3da79a4de4 Comment Tacotron2 model 2021-10-20 18:14:04 +00:00
Eren Gölge 92b6d98443 Set pitch frame alignment wrt spec computation 2021-10-20 18:12:38 +00:00
Eren Gölge 0a3d1cc7ee Pass speaker manager to the model in synthesizer 2021-10-20 18:11:36 +00:00
Eren Gölge 588da1a24e Simplify grad_norm handling in trainer 2021-10-19 16:33:04 +00:00
Eren Gölge 3c7848e9b1 Don't OOR values in train console log 2021-10-19 16:32:16 +00:00
Eren Gölge c514351c0e Refactor multi-speaker init in BaseTTS-Tacotron1-2 2021-10-18 08:55:45 +00:00
Eren Gölge 127571423c Update multi-speaker init in BaseTTS 2021-10-18 08:54:41 +00:00
Eren Gölge a0a5d580e9 Approximate audio length from file size 2021-10-18 08:54:02 +00:00
Eren Gölge b4b890df03 Update trainer's initialization 2021-10-18 08:53:19 +00:00
Eren Gölge fcbfc53cb7 Fix linter 2021-10-15 10:24:19 +00:00
Eren Gölge 700b056117 Update Synthesizer multi-speaker handling 2021-10-15 10:21:12 +00:00
Eren Gölge 073a2d2eb0 Refactor VITS multi-speaker initialization 2021-10-15 10:20:00 +00:00
Eren Gölge 0565457faa Fix #846 2021-10-14 14:46:14 +00:00
Eren Gölge e15bc157d8 Fix #873 2021-10-14 14:39:45 +00:00
Eren Gölge 21cc0517a3 Fix WaveRNN test 2021-10-01 10:21:37 +00:00
Eren Gölge 4dbe7ed0de Fix all-zero duration case for GlowTTS 2021-10-01 09:24:26 +00:00
Eren Gölge 37959ad0c7 Make linter 2021-09-30 23:02:16 +00:00
Eren Gölge 0b1986384f Make style 2021-09-30 16:21:18 +00:00
Eren Gölge 7edbe04fe0 Fix WaveRNN config and test 2021-09-30 16:20:12 +00:00
Eren Gölge 55d9209221 Remote STT tokenizer 2021-09-30 14:58:26 +00:00
Eren Gölge ba2b8c827f Update `train_tts.py` and `train_vocoder.py` 2021-09-30 14:47:56 +00:00
Eren Gölge 2e9b6b4f90 Refactor Speaker Encoder training 2021-09-30 14:47:56 +00:00
Eren Gölge 043dca61b4 Rename `load_meta_data` as `load_tts_data` 2021-09-30 14:47:56 +00:00
Eren Gölge 9f23ad6a0f Fix imports 2021-09-30 14:47:56 +00:00
Eren Gölge 16b70be0dd Add `_set_model_args` to BaseModel 2021-09-30 14:47:56 +00:00
Eren Gölge 9a0d8fa027 Update `copy_model_files()` 2021-09-30 14:47:56 +00:00
Eren Gölge 4163b4f2e4 Update Tacotron models 2021-09-30 14:47:56 +00:00
Eren Gölge e27feade38 Fixup wavernn 2021-09-30 14:47:56 +00:00
Eren Gölge 45889804c2 Update VITS 2021-09-30 14:47:56 +00:00
Eren Gölge 4f94f91305 Update WaveRNN 2021-09-30 14:47:56 +00:00
Eren Gölge 3d5205d66f Update WaveGrad 2021-09-30 14:47:56 +00:00
Eren Gölge fd95926009 Update GlowTTS 2021-09-30 14:47:56 +00:00
Eren Gölge 4baecdf92a Update GAN for Trainer_v2 2021-09-30 14:47:56 +00:00
Eren Gölge a156a40b47 Update ForwardTTS for Trainer_v2 2021-09-30 14:19:19 +00:00
Eren Gölge d9df33f837 Update `align_tts` for trainer_v2 2021-09-30 14:18:10 +00:00
Eren Gölge 8ada870a57 Refactor `trainer.py` for v2 2021-09-30 14:16:34 +00:00
Eren Gölge 7f388f26e3 Bump up to v0.3.1 2021-09-17 23:53:22 +00:00
Eren Gölge 2766dd1d6e
Fix #813 - GlowTTS training (#814) 
* Fix #813

* Update glow_tts recipe

* Fix glow-tts test

* Linter fix

* Run data dep init only in training
 2021-09-17 20:06:55 +02:00
Eren Gölge f563415052 Bump up to v0.3.0 2021-09-13 09:40:38 +00:00
Eren Gölge a97dc8d09f Fix trainer malformatted print 2021-09-13 08:32:02 +00:00
Eren Gölge 91bebebe18 Add new models to `.models.json` 
SpeedySpeech model using `ForwardTTS`
UnivNet model fine-tuned on TacotronDDC_ph spectrograms
 2021-09-13 08:22:14 +00:00
Eren Gölge 1ea011571a Update SpeedySpeech config 2021-09-12 15:33:27 +00:00
Eren Gölge cbbc9e0172 Add FastSpeechConfig 2021-09-11 10:20:37 +00:00
Eren Gölge 26f76fce22 Remove SpeedySpeech from .models.json 2021-09-10 17:47:27 +00:00
Eren Gölge d97952611d Remove unused import 2021-09-10 17:31:41 +00:00
Eren Gölge 7d8f77385a Use `glow-tts` in synthesis tests 2021-09-10 17:27:33 +00:00
Eren Gölge d5f256b34c Update tacotron `r` init 2021-09-10 17:26:23 +00:00
Eren Gölge ab37fa9c39 Edit AlignTTS 2021-09-10 17:25:00 +00:00
Eren Gölge 66732025e1 Add `base_model` field to `forward_tts` configs 2021-09-10 17:23:48 +00:00
Eren Gölge d6e29ef98a Style update 2021-09-10 08:30:33 +00:00
Eren Gölge a89eb12aca Fix glow_tts imports 2021-09-10 08:29:51 +00:00
Eren Gölge 570d5971be Implement `ForwardTTSLoss` 2021-09-10 08:29:12 +00:00
Eren Gölge 0541a25e90 Remove `fastpitch.py` and `speedy_speech.py` 2021-09-10 08:27:48 +00:00
Eren Gölge 3c16013199 Fix Vits imports 2021-09-10 08:26:34 +00:00
Eren Gölge 742f9c54da Warn user if nan in GL 2021-09-10 08:26:05 +00:00
Eren Gölge ed4b1d8514 Test `TTS.tts.utils.helpers` 2021-09-10 08:25:21 +00:00
Eren Gölge 8b7e094bde Implement `forward_tts` 
- Generic API for feed-forward TTS models (FastPitch, SpeedySpeech)

- Tests for `forward-tts`

- Edit  FastPitchConfig and SpeedySpeechConfig to use `forward_tts`
 2021-09-10 08:24:33 +00:00
Eren Gölge 3c740d4893 Style extract_tts_spectrogram.py 2021-09-10 08:21:21 +00:00
Eren Gölge bfc6ceac29 Move MAS to `TTS.tts.utils.helpers` 2021-09-09 10:57:19 +00:00
Eren Gölge 2dfc5bdd11 Fix best_model_path init if no best_mode 2021-09-09 09:01:52 +00:00
Eren Gölge abf5e48177 Fix logging current learning rate in trainer 2021-09-09 09:01:04 +00:00
Eren Gölge 6c4c1065b0 Fix trainer's scheduler restoring 2021-09-09 09:00:27 +00:00
Eren Gölge 807f1d3817 Fix `extract_tts_spectrograms.py` model init 2021-09-09 08:59:55 +00:00
Eren Gölge 537c8576ec Stage `TTS.tts.utils.helpers` 2021-09-08 13:35:18 +00:00
Eren Gölge 4761853c5c Fix imports 2021-09-08 13:34:40 +00:00
Eren Gölge e20ea57c87 Update comment and add a warning 2021-09-07 12:23:32 +00:00
Eren Gölge 82598f3fdb Bump up to v0.2.2 2021-09-06 16:59:41 +00:00
Eren Gölge 4cc544bc46 Add FastPitch model to `.models.json` 2021-09-06 16:59:22 +00:00
Eren Gölge 2c4bbbf9b9 Use pyworld for pitch 2021-09-06 15:16:58 +00:00
Eren Gölge c1513ec4cd Plot pitch over spectrogram 2021-09-06 15:16:58 +00:00
Eren Gölge d847a68e42 Reformat multi-speaker handling in GlowTTS 2021-09-06 15:16:58 +00:00
Eren Gölge 8d41060d36 Plot unnormalized pitch by `FastPitch` 2021-09-06 15:16:58 +00:00
Eren Gölge 2b59da802c Fix loader setup in `base_tts` 2021-09-06 15:16:58 +00:00
Eren Gölge 76c4929ab2 Fix attn mask reading bug 2021-09-06 15:16:58 +00:00
Eren Gölge 91a70e80b2 Refactor TTSDataset 
Return a dict by `collate`
Refactor batch handling in `collate`
A couple of bug fixes
 2021-09-06 15:16:58 +00:00
Eren Gölge 29248536c9 Update `PositionalEncoding` 2021-09-06 15:16:58 +00:00
Eren Gölge 4672889549 Update `generic.FFTransformer` 2021-09-06 15:16:58 +00:00
Eren Gölge 2bf9e83c49 FastPitch refactor and commenting 2021-09-06 15:16:58 +00:00
Eren Gölge 59b24e66cf Add `AlignerNetwork` 2021-09-06 15:16:58 +00:00
Eren Gölge 648655fa03 Add `PitchExtractor` and return dict by `collate` 2021-09-06 15:16:58 +00:00
Eren Gölge debf772ec5 Implement binary alignment loss 2021-09-06 15:16:58 +00:00
Eren Gölge 6e9d4062f2 Add `sort_by_audio_len` option 2021-09-06 15:16:58 +00:00
Eren Gölge 59d52a4cd8 Disable autcast for criterions 2021-09-06 15:16:58 +00:00
Eren Gölge 98a7271ce8 Refactor FastPitchv2 2021-09-06 15:16:58 +00:00
Eren Gölge e429afbce4 Enable aligner for FastPitch 2021-09-06 15:16:58 +00:00
Eren Gölge 81c228a2d8 Update FastPitch don't detach duration network inputs 2021-09-06 15:16:58 +00:00
Eren Gölge ca29033ef4 Refactor FastPitch model 2021-09-06 15:16:58 +00:00
Eren Gölge 42862f7fdb Format style of the recipes 2021-09-06 15:16:58 +00:00
Eren Gölge 5d59100a88 Don't use align_score for models with duration predictor 2021-09-06 15:16:58 +00:00
Eren Gölge fac9dbe661 Update FastPitchLoss 2021-09-06 15:16:58 +00:00
Eren Gölge b81560607b Update docstrings 2021-09-06 15:16:58 +00:00
Eren Gölge 57b3aec1b9 Update docstring format 2021-09-06 15:16:58 +00:00
Eren Gölge 7692bfe7f8 Update FastPitch config 2021-09-06 15:16:58 +00:00
Eren Gölge 8584f2b82d Update docstring format 2021-09-06 15:16:58 +00:00
Eren Gölge b7caad39e0 Make optional to detach duration predictor input 2021-09-06 15:16:58 +00:00
Eren Gölge 9af42f7886 Restore `last_epoch` of the scheduler 2021-09-06 15:16:58 +00:00
Eren Gölge aacbb3ed77 Fix SpeakerManager usage in `synthesize.py` 2021-09-06 15:16:58 +00:00
Eren Gölge 545a00fc04 Use absolute paths of the attention masks 2021-09-06 15:16:58 +00:00
Eren Gölge bc396c393f Add FastPitch model and FastPitchconfig 2021-09-06 15:16:58 +00:00
Eren Gölge 5a6ffaee08 Add yin based pitch computation 2021-09-06 15:16:58 +00:00
Eren Gölge e802b24ad0 Compute mean and std pitch 2021-09-06 15:16:58 +00:00
Eren Gölge 8fffd4e813 Don't print computed phonemes 
It causes noise in logs
 2021-09-06 15:16:58 +00:00
Eren Gölge d085642ac1 Cache pitch features 
Cache the features at the beginning of `BaseTTS` training.
 2021-09-06 15:16:58 +00:00
Eren Gölge 7590c7db7a Fix `base_tacotron` `aux_input` handling 2021-09-06 15:16:58 +00:00
Eren Gölge db32162eae Fix `FastPitchLoss` 2021-09-06 15:16:58 +00:00
Eren Gölge 94e8e0d416 Fix configs 2021-09-06 15:16:58 +00:00
Eren Gölge 0f19f8c911 Fix `compute_attention_masks.py` 2021-09-06 15:16:58 +00:00
Eren Gölge 994f2be2c1 Add comput_f0 field 2021-09-06 15:16:58 +00:00
Eren Gölge c8d999b010 Add FastPitchLoss 2021-09-06 15:16:58 +00:00
Eren Gölge fba257104d Compute F0 using librosa 2021-09-06 15:16:58 +00:00
Katsuya Iida 165e5814af
Update Japanese phonemizer (#758) 
* Update default ja vocoder

* update

* Japanese phonemizer test

* Run make style

Co-authored-by: Eren Gölge <egolge@coqui.ai>
 2021-09-01 09:33:15 +02:00
Eren Gölge 2b7e55f01f Fix vits args types 2021-08-30 23:24:20 +00:00
Eren Gölge b910a6ddce Bump up to v0.2.1 2021-08-30 16:31:24 +00:00
Eren Gölge d16da949a5 Merge branch 'fix_distribute' into dev 2021-08-30 16:31:07 +00:00
Eren Gölge 6782d3eab7 Fix linter issues ofr p3.6 2021-08-30 16:18:33 +00:00
Eren Gölge 738eee0cf9 Fix style 2021-08-30 13:12:13 +00:00
Eren Gölge 5255e089e6 Fix #767 2021-08-30 13:10:08 +00:00
Eren Gölge c560114324 Fix #750 2021-08-30 13:06:50 +00:00
Eren Gölge 18b2e41e5a Use `coqui_tts` as the default run name 2021-08-30 12:56:47 +00:00
Eren Gölge 9c86f1ac68 Fix usage of abstract class in vocoders 2021-08-30 08:10:35 +00:00
Eren Gölge 18da8f5dbd Update pylint 2.10.2 and fix lint issues 2021-08-30 08:10:35 +00:00
Eren Gölge f186856e5d Add option to sort input sequnce by audio len 2021-08-30 08:10:35 +00:00
Eren Gölge 2620f62ea8 Move duration_loss inside VitsGeneratorLoss 2021-08-27 07:07:07 +00:00
Eren Gölge 1692b8e4d9
Merge pull request #726 from fijipants/patch-1 
Fix bug with log_func
 2021-08-26 22:11:29 +02:00
Eren Gölge 49e1181ea4 Fixes for the vits model 2021-08-26 17:15:09 +00:00
Eren Gölge 5911eec3b1 Small trainer refactoring 
1. Use a single Gradscaler for all the optimizers
2. Save terminal logs to a file. In DDP mode, each worker creates `trainer_N_log.txt`.
3. Fixes to allow only the main worker (rank==0) writing to Tensorboard
4. Pass parameters owned by the target optimizer to the grad_clip_norm
 2021-08-26 17:08:58 +00:00
fijipants e9e01b09b0 Fix bug with log_func 2021-08-18 19:59:51 -04:00
fijipants 8f57f8adfd Update synthesizer.py 2021-08-18 19:56:52 -04:00
Eren Gölge 3ab8cef99e Fix VITS model SPD 2021-08-18 14:55:46 +00:00
Eren Gölge c5d1dd9d1b Fix restoring best_loss 
Keep the default value if model checkpoint has no `model_loss`
 2021-08-17 12:12:36 +00:00
Eren Gölge c8bbcdfd07 Fix `test_run` for DDP 2021-08-13 19:39:02 +00:00
Eren Gölge 7c0d564965 Syncronize DDP processes 2021-08-13 10:40:50 +00:00
Eren Gölge ecf5f17dca Fix distribute.py and ddp training 2021-08-12 22:22:32 +00:00
Eren Gölge b02c4fe347 Bump up to v0.2.0 2021-08-11 08:15:39 +00:00
Eren Gölge 537bc8487a Print model count when listing modelsk 2021-08-10 16:25:11 +00:00
Eren Gölge 09ed8426e8 Add the models released with v0.2.0 2021-08-10 15:46:31 +00:00
Eren Gölge 39004484b9 Fix 🐛 
Fix synthesizer multi-speaker init
Fix #712
 2021-08-10 12:56:32 +00:00
Eren Gölge c8b9ca3d71 Fix Tacotron num_char init 2021-08-10 08:56:34 +00:00
Eren Gölge 7eb94f760b Remove Ruslan model 2021-08-09 21:48:36 +00:00
Eren Gölge 6af03ac476 Fix `num_char` init in Tacotron models 2021-08-09 21:46:15 +00:00
Ayush Chaurasia e685ddfca7 Update trainer.py 2021-08-09 18:37:46 +00:00
Ayush Chaurasia 28870f8df4 update docstring 2021-08-09 18:35:35 +00:00
Ayush Chaurasia 8a246cbb66 Update trainer.py 2021-08-09 18:35:08 +00:00
Ayush Chaurasia f3e9d61330 Refactor logging initialization 2021-08-09 18:35:08 +00:00
Ayush Chaurasia 79b74a989d Update: add_text 2021-08-09 18:34:38 +00:00
Ayush Chaurasia 9fcf48b760 Delete logger_base.py 2021-08-09 18:34:00 +00:00
Ayush Chaurasia 290972fd35 reformat 2021-08-09 18:34:00 +00:00
Ayush Chaurasia 936a47504d Update Logger API, recipes 2021-08-09 18:34:00 +00:00
Ayush Chaurasia f63cf46c55 Unified logger API 2021-08-09 18:34:00 +00:00
Ayush Chaurasia f4434da5a3 Update disabled structure 2021-08-09 18:31:16 +00:00
Ayush Chaurasia f606741dc4 Add artifacts logging , wandb args 2021-08-09 18:31:16 +00:00
Ayush Chaurasia f5e50ad502 WandbLogger 2021-08-09 18:27:06 +00:00
Eren Gölge 06018251e6 Add VITS and GlowTTS class docs 🗒️ 2021-08-09 18:02:36 +00:00
Eren Gölge 6a7275881d Add VitsConfig docstring 2021-08-09 18:02:36 +00:00
Eren Gölge f7a72552f1 Make duration predictor dropout configurable 2021-08-09 18:02:36 +00:00
Eren Gölge c312acac7d Implement VITS model 🚀 
VITS model implementation built on Glow TTS and HiFiGAN
layers.
 2021-08-09 18:02:36 +00:00
Eren Gölge 060e746e21 Add `do_amp_to_db` option 2021-08-09 18:02:36 +00:00
Eren Gölge e94c1f894d Simplify `console_logger` 2021-08-09 18:02:36 +00:00
Eren Gölge dd55960732 Update `synthesizer.py` 
Fixes and changes for multi-speaker model init and custom symbols  made
by mode.make_symbols()
 2021-08-09 18:02:36 +00:00
Eren Gölge 232a5abb6a Update `tts.setup_model` 
Run `model.make_symbols()` if availabe to set the symbol list
 2021-08-09 18:02:36 +00:00
Eren Gölge f5a6aa974f Modify `symbols.py` not to add _arpanet 2021-08-09 18:02:36 +00:00
Eren Gölge d4deb2716f Modify `get_optimizer` to accept a model argument 2021-08-09 18:02:36 +00:00
Eren Gölge 003e5579e8 Enable `custom_symbols` in text processing 
Models can define their own custom symbols lists with custom
`make_symbols()`
 2021-08-09 18:02:36 +00:00
Eren Gölge bd4e29b4dd Add `compute_linear_spec=False` to `BaseTTSConfig` 2021-08-09 18:02:36 +00:00
Eren Gölge 960a35a121 Add `scheduler_after_epoch` to `BaseTrainingConfig` 2021-08-09 18:02:36 +00:00
Eren Gölge e4648ffef1 Fix multi-speaker init of Tacotron models & tests 2021-08-09 18:02:36 +00:00
Eren Gölge 01324c8e70 Update `base_tts.py` 
Enable calling `make_symbols()` from the model if defined.
Compatibility changes for end2end `tts` models in batch formatting.
Changes in multi-speaker initialization.
Modify `test_run()` to work with dict output iof `synthesis`
 2021-08-09 18:02:36 +00:00
Eren Gölge bf562cf437 Update `trainer.py` 
Fix multi-speaker initialization of models. Add changes for end2end`tts`
models.
 2021-08-09 18:02:36 +00:00
Agrin Hilmkil ced4cfdbbf Allow saving / loading checkpoints from cloud paths (#683) 
* Allow saving / loading checkpoints from cloud paths

Allows saving and loading checkpoints directly from cloud paths like
Amazon S3 (s3://) and Google Cloud Storage (gs://) by using fsspec.

Note: The user will have to install the relevant dependency for each
protocol. Otherwise fsspec will fail and specify which dependency is
missing.

* Append suffix _fsspec to save/load function names

* Add a lower bound to the fsspec dependency

Skips the 0 major version.

* Add missing changes from refactor

* Use fsspec for remaining artifacts

* Add test case with path requiring fsspec

* Avoid writing logs to file unless output_path is local

* Document the possibility of using paths supported by fsspec

* Fix style and lint

* Add missing lint fixes

* Add type annotations to new functions

* Use Coqpit method for converting config to dict

* Fix type annotation in semi-new function

* Add return type for load_fsspec

* Fix bug where fs not always created

* Restore the experiment removal functionality
 2021-08-09 18:02:36 +00:00
Eren Gölge d9e18e009b Skip phoneme cache pre-compute if the path exists 2021-08-09 18:02:36 +00:00
Eren Gölge 6c131d168e Bump the version to 0.1.3 2021-07-26 21:32:27 +02:00
Eren Gölge febd6105b5 Update default vocoder for de-thorsten 2021-07-26 16:08:52 +02:00
Eren Gölge 4b7b88dd3d Add fullband-melgan DE vocoder 2021-07-26 15:38:30 +02:00
Eren Gölge 764f684e1b Fix `server.py` for multi-speaker models 2021-07-26 15:38:30 +02:00
Eren Gölge 75b201c6c1
Merge pull request #673 from coqui-ai/fix_stopnet 
Fix stopnet training for Tacotron models
 2021-07-24 12:25:38 +02:00
Eren Gölge fc0c4600bd Fix stopnet training 2021-07-24 11:39:54 +02:00
Eren Gölge 30eed347b6
Merge pull request #581 from Edresson/dev 
Compute speaker embeddings in batch for the LSTM  Speaker Encoder and Compute embeddings/ finding chars using config file.
 2021-07-23 17:22:51 +02:00
Edresson Casanova d5adc35fdf
Add docstring to compute_embeddings script 2021-07-21 07:16:10 -03:00
Eren Gölge 05c75aa9d5 Fix linter issues 2021-07-16 13:37:38 +02:00
Eren Gölge 58cc414477 Fix WaveGrad `test_run` 2021-07-16 13:02:25 +02:00
WeberJulian 25832eb97b Changes for review 2021-07-15 11:38:45 +02:00
Edresson b1620d1f3f remove ignore generate eval flag 2021-07-15 03:34:28 -03:00
WeberJulian c79a82ed07 refix linter 2021-07-13 23:12:18 +02:00
WeberJulian 7d92b30946 Fix tests 2021-07-13 23:00:34 +02:00
WeberJulian 32974dd6a9 Fix test sentences synthesis 2021-07-13 16:07:13 +02:00
Edresson d906fea08c lint fix and eval as argparse in extract tts spectrograms 2021-07-13 02:15:31 -03:00
Edresson 2e5baffa9c Merge fix and eval split as argparse 2021-07-13 01:47:32 -03:00
Eren Gölge 93a74cbb71
Merge pull request #628 from Aloento/patch-2 
Change to _get_preprocessor_by_name
 2021-07-11 22:17:50 +02:00
Edresson 4eac1c4651 bug fix on train_encoder and unit tests 2021-07-11 12:00:39 -03:00
Aloento 6e3e6d5756
Change to _get_preprocessor_by_name 2021-07-08 09:53:13 +02:00
Eren Gölge 8fbadad68e Bump up to v0.1.2 2021-07-06 14:44:59 +02:00
eren golge 3c0454490f Fix #616 2021-07-06 14:44:03 +02:00
Eren Gölge 0c347624e7 Bump up version to v0.1.1 2021-07-04 11:46:36 +02:00
Eren Gölge a05b234080 Raise an error when multiple GPUs are in use 
User must define the target GPU by `CUDA_VISIBLE_DEVICES` and
use `distribute.py` for multi-gpu training.
 2021-07-04 11:25:49 +02:00
Eren Gölge 270c3823eb Fix #608 2021-07-04 11:19:31 +02:00
Eren Gölge c25a2184e7 Add docs for `SpeakerManager` 2021-07-03 13:55:27 +02:00
Eren Gölge f382e4c700 Fix linter warnings 2021-07-03 13:30:24 +02:00
Eren Gölge 9e7824fe35 Fix UnivNet inference code 2021-07-02 10:48:34 +02:00
Eren Gölge 168f97cbe9 Let `Synthesizer` use the speaker manager out of the model 2021-07-02 10:47:55 +02:00
Eren Gölge 196876feb1 Fix `ModelManager` model download 2021-07-02 10:47:05 +02:00
Eren Gölge 9352cb4136 Format Align TTS docstrings 2021-07-02 10:45:58 +02:00
Eren Gölge 95ad72f38f Fix glow tts initialization 2021-07-02 10:45:37 +02:00
Eren Gölge 40b0b5365e Let `get_characters` return `num_chars` 2021-07-02 10:45:00 +02:00
Eren Gölge 0fa6a8c9b8 Fix glow tts default parameters 2021-07-02 10:44:23 +02:00
Eren Gölge a4c658f5ef Fix for using the `Synthesizer` out of the model 2021-07-02 10:43:38 +02:00
Eren Gölge db47f4f105 Update `.models.json` 2021-07-02 10:43:00 +02:00
Eren Gölge 2e1a428b83 Update glowtts docstrings and docs 2021-06-30 14:30:55 +02:00
Eren Gölge 5723eb4738 Fix config init in `process_args` 2021-06-29 16:41:08 +02:00
Eren Gölge 4b5421b42f Remove FAQ link from README.md 2021-06-29 13:20:40 +02:00
Eren Gölge 47b3b10d6d Bump up to v0.1.0 🚀 2021-06-29 13:07:59 +02:00
Eren Gölge 7ec5c31898 Merge branch 'univnet' into trainer-api 2021-06-29 10:27:12 +02:00
Eren Gölge 51398cd15b Add docstrings and typing for `audio.py` 2021-06-28 17:03:47 +02:00
Eren Gölge ae6405bb76 Docstrings for `Trainer` 2021-06-28 17:03:47 +02:00
Eren Gölge 6b265ae8e3 Docstring update 2021-06-28 17:03:47 +02:00
Eren Gölge ab563ce7cd Start training by config.json using `register_config` 2021-06-28 17:03:47 +02:00
Eren Gölge b3c073c99b Allow runing full path scripts with `distribute.py` 2021-06-28 17:03:47 +02:00
Eren Gölge d42d1c02ea Use `torch.linalg.qr` for pytorch > `v1.9.0` 2021-06-28 17:03:47 +02:00
Eren Gölge fbba37e01e Fix loading the `amp` scaler from a checkpoint 🛠️ 2021-06-28 17:03:47 +02:00
Eren Gölge a7617d8ab6 Add 🐍 python 3.9 to CI 2021-06-28 17:03:47 +02:00
Eren Gölge 9790eddada Fix wrong argument name 🛠️ 2021-06-28 17:03:47 +02:00
Eren Gölge 932ab107ae Docstring edit in `TTSDataset.py` ✍️ 2021-06-28 17:03:47 +02:00
Eren Gölge cfa5041db7 Fix `eval_log` for `gan.py` 🛠️ 2021-06-28 17:03:47 +02:00
Eren Gölge d700845b10 Move `TorchSTFT` to `utils.audio` 2021-06-28 17:03:47 +02:00
Eren Gölge 5b89cb4fec Fixup `trainer.py` 🛠️ 2021-06-28 17:03:47 +02:00
Eren Gölge 8c74f054f0 Enable support for 🐍 python 3.10 
Bump up versions numpy 1.19.5 and TF 2.5.0
 2021-06-28 17:03:47 +02:00
Eren Gölge 9455a2b01e Apply small fixes for API compatibility 2021-06-28 17:03:47 +02:00
Eren Gölge a5d5bc9063 Print `max_decoder_steps` when model reaches the limit 2021-06-28 17:03:47 +02:00
Eren Gölge e30f245e06 Update `synthesizer` for speaker and model init 2021-06-28 17:03:47 +02:00
Eren Gölge 15fa31b595 fixup configs 2021-06-28 17:03:47 +02:00
Eren Gölge f23b228e24 Update `speaker_manager` 2021-06-28 17:03:47 +02:00
Eren Gölge e53616078a Fixup `utils` for the trainer 2021-06-28 17:03:47 +02:00
Eren Gölge 106b63d8a9 Update `vocoder` utils 2021-06-28 17:03:47 +02:00
Eren Gölge 45947acb60 Update `TTS.bin` scripts for the new API 2021-06-28 17:03:47 +02:00
Eren Gölge d7225eedb0 Update `vocoder` datasets and `setup_dataset` 2021-06-28 17:03:20 +02:00
Eren Gölge d18198dff8 Implement `setup_model` for vocoder models 2021-06-28 17:03:20 +02:00
Eren Gölge e949e7ad58 Update vocoder models 2021-06-28 17:03:19 +02:00
Eren Gölge 51005cdab4 Update `tts.models.setup_model` 2021-06-28 17:03:19 +02:00
Eren Gölge 7b8c15ac49 Create base 🐸TTS model abstraction for tts models 2021-06-28 17:03:19 +02:00
Eren Gölge a358f74a52 Update vocoder model configs 2021-06-28 17:03:19 +02:00
Eren Gölge 786170fe7d Update tts model configs 2021-06-28 17:03:19 +02:00
Eren Gölge 98298ee671 Implement unified IO utils 2021-06-28 17:03:19 +02:00
Eren Gölge c7aad884cd Implement unified trainer 2021-06-28 17:03:19 +02:00
Eren Gölge 6d7b5fbcde `tts` model abstraction with `TTSModel` 2021-06-28 17:03:19 +02:00
Eren Gölge d4dbd89752 fix calculation of `loader_start_time` 2021-06-28 17:03:19 +02:00
Eren Gölge c754a0e17d `TrainerAbstract` and related updates for `TrainerTTS` 2021-06-28 17:03:19 +02:00
Eren Gölge 00c82c516d rename to 2021-06-28 17:03:19 +02:00
Eren Gölge 166f0aeb9a merge if branches with the same implementation 2021-06-28 17:03:19 +02:00
Eren Gölge 03494ad642 adjust `distribute.py` for the `train_tts.py` 2021-06-28 17:03:19 +02:00
Eren Gölge fdfb18d230 downsize melgan test model size 2021-06-28 17:03:19 +02:00
Eren Gölge 25238e0658 fix glow-tts `inference()` 2021-06-28 17:03:19 +02:00
Eren Gölge 419735f440 refactor and fix multi-speaker training in Trainer and Tacotron models 2021-06-28 17:03:19 +02:00
Eren Gölge 269e5a734e add max_decoder_steps argument to tacotron models 2021-06-28 17:03:19 +02:00
Eren Gölge b3324bd914 fix speaker_manager init 2021-06-28 17:03:19 +02:00
Eren Gölge 2c38ef8441 use get_speaker_manager in Trainer and save speakers.json file when 
needed
 2021-06-28 17:03:19 +02:00
Eren Gölge d6b2b6add6 make style and linter fixes 2021-06-28 17:03:19 +02:00
Eren Gölge 802d461389 Compute d_vectors and speaker_ids separately in TTSDataset 2021-06-28 17:03:19 +02:00
Eren Gölge db6a97d1a2 rename external speaker embedding arguments as `d_vectors` 2021-06-28 17:03:19 +02:00
Eren Gölge 9042ae9195 use `to_cuda()` for moving data in `format_batch()` 2021-06-28 17:03:19 +02:00
Eren Gölge f82f1970b8 change `to(device)` to `type_as` in models 2021-06-28 17:03:19 +02:00
Eren Gölge 9c94b0c5c0 init `durations = None` 2021-06-28 17:03:19 +02:00
Eren Gölge 1fa15c195a docstring fix 2021-06-28 17:03:19 +02:00
Eren Gölge 1c8a3d7c86 make style 2021-06-28 17:03:19 +02:00
Eren Gölge 8cdd423234 styling formatting.py 2021-06-28 17:03:19 +02:00
Eren Gölge 30211512a4 fix type annotations 2021-06-28 17:03:19 +02:00
Eren Gölge b22b7620c3 update glow-tts output shapes to match [B, T, C] 2021-06-28 17:03:19 +02:00
Eren Gölge 8381379938 formating `cond_input` with a function in Tacotron models 2021-06-28 17:03:19 +02:00
Eren Gölge ef4ea9e527 update imports for `formatters` 2021-06-28 17:03:19 +02:00
Eren Gölge 6c495c6a6e fix glow-tts inference and forward functions for handling `cond_input` 
and refactor its test
 2021-06-28 17:03:19 +02:00
Eren Gölge f840268181 refactor `SpeakerManager` 2021-06-28 17:03:19 +02:00
Eren Gölge 421194880d linter fixes 2021-06-28 17:03:19 +02:00
Eren Gölge 8e52a69230 delete separate tts training scripts and pre-commit configuration 2021-06-28 17:03:19 +02:00
Eren Gölge d96ebcd6d3 make style 2021-06-28 17:03:19 +02:00
Eren Gölge b643e8b37c `logging/__init__.py` 2021-06-28 17:03:19 +02:00
Eren Gölge 0cee5042a9 fix logger imports 2021-06-28 17:03:19 +02:00
Eren Gölge 72dceca52c import missings 2021-06-28 17:03:19 +02:00
Eren Gölge 0eec238429 remove redundant imports 2021-06-28 17:03:19 +02:00
Eren Gölge b500338faa make style 2021-06-28 17:03:19 +02:00
Eren Gölge 469d2e620a update extract_tts_spectrogram for `cond_input` API of the models 2021-06-28 17:03:19 +02:00
Eren Gölge 5ab28fa618 update `extract_tts_spec...` using `SpeakerManager` 2021-06-28 17:03:19 +02:00
Eren Gölge c392fa4288 update `extract_tts_spectrograms` for the new model API 2021-06-28 17:03:19 +02:00
Eren Gölge 8f47f95998 correct import of `load_meta_data` 
remove redundant import
 2021-06-28 17:03:19 +02:00
Eren Gölge c680a07a20 fix `Synthesized` for the new `synthesis()` 2021-06-28 17:03:19 +02:00
Eren Gölge 73bf9673ed revert logging.info to print statements for trainer 2021-06-28 17:03:19 +02:00
Eren Gölge d25f017b42 update `setup_model.py` imports 2021-06-28 17:03:19 +02:00
Eren Gölge bb355b7441 update align_tts.py model for the trainer 2021-06-28 17:03:19 +02:00
Eren Gölge 9203b863d9 update align_tts_loss for trainer 2021-06-28 17:03:19 +02:00
Eren Gölge fc9a0fb8ce update aling_tts_config for the trainer 2021-06-28 17:03:19 +02:00
Eren Gölge e298b8e364 update trainer.py for better logging handling, restoring models and 
rename init_ functions with get_
 2021-06-28 17:03:19 +02:00
Eren Gölge b8a4af4010 update `synthesis.py` for being more generic 2021-06-28 17:03:19 +02:00
Eren Gölge c70d0c9dae update `speedy_speech.py` model for trainer 2021-06-28 17:03:19 +02:00
Eren Gölge 06ee57d816 update `speedy_speecy_config.py` for the trainer 2021-06-28 17:03:19 +02:00
Eren Gölge 4e910993f1 update tacotron model to return `model_outputs` 2021-06-28 17:03:19 +02:00
Eren Gölge bb4deee64c update glow-tts for the trainer 2021-06-28 17:03:19 +02:00
Eren Gölge 9134c7dfb6 update `sequence_mask` import globally 2021-06-28 17:03:19 +02:00
Eren Gölge b2218e882a update `glow_tts_config.py` for setting the optimizer and the scheduler 2021-06-28 17:03:19 +02:00
Eren Gölge 891631ab47 typing annotation for the trainer 2021-06-28 17:03:19 +02:00
Eren Gölge 5f07315722 add trainer and train_tts 2021-06-28 17:03:19 +02:00
Eren Gölge 34f8a74e4d remove `truncated` from synthesizer 2021-06-28 17:03:19 +02:00
Eren Gölge 178eccbc16 update console logger 2021-06-28 17:03:19 +02:00
Eren Gölge f4f83b6379 update `synthesis.py` for the trainer 2021-06-28 17:03:19 +02:00
Eren Gölge 130781dab6 remove `tts.generic_utils` as all the functions are moved to other files 2021-06-28 17:03:19 +02:00
Eren Gölge 535a458f40 update Tacotron models for the trainer 2021-06-28 17:03:19 +02:00
Eren Gölge bdbfc95618 add `gradual_training` argument to tacotron.py 2021-06-28 17:03:19 +02:00
Eren Gölge 5a2e75f0ee import missings for tacotron.py 2021-06-28 17:03:19 +02:00
Eren Gölge da7d10e53c mode `setup_model()` to `models/__init__.py` 2021-06-28 17:03:19 +02:00
Eren Gölge ca302db7b0 add sequence_mask to `utils.data` 2021-06-28 17:03:19 +02:00
Eren Gölge 844abb3b1d `setup_loss()` in `layer/__init__.py` 2021-06-28 17:03:19 +02:00
Eren Gölge a20a1c7d06 rename preprocess.py -> formatters.py 2021-06-28 17:03:19 +02:00
Eren Gölge b9bccbb243 move load_meta_data and related functions to `datasets/__init__.py` 2021-06-28 17:03:19 +02:00
Eren Gölge d09385808a set test_sentences in config 2021-06-28 17:03:19 +02:00
Eren Gölge 8def3c87af trainer-API updates 2021-06-28 17:03:19 +02:00
Eren Gölge 42554cc711 rename MyDataset -> TTSDataset 2021-06-28 17:03:19 +02:00
Edresson 1c4e806f54 use speaker manager on compute embeddings script 2021-06-27 03:35:34 -03:00
Edresson Casanova eb84bb2bc8
Merge branch 'dev' into dev 2021-06-26 15:32:19 -03:00
Eren Gölge 987cf1178b Bump up to v0.0.16 2021-06-25 14:44:56 +02:00
Michael Hansen 3f172b84d8 Fix linting issues 2021-06-25 14:41:31 +02:00
Michael Hansen 4d8426fa0a Use eSpeak IPA lexicons by default for phoneme models 2021-06-25 14:41:05 +02:00
Michael Hansen 618b509204 Use combined characters available in TTS phonemes (like ç) 2021-06-25 14:41:05 +02:00
Michael Hansen da6f6a4a01 Update docstring for clean_gruut_phonemes 2021-06-25 14:41:05 +02:00
Michael Hansen 47191f3ecc Add tests for gruut phonemization 2021-06-25 14:41:05 +02:00
Michael Hansen 67869e77f9 Use gruut for phonemization 2021-06-25 14:41:05 +02:00
Eren Gölge 788992093d Add UnivNet vocoder 🚀 2021-06-23 13:51:04 +02:00
Eren Gölge 64fd59204c Use `torch.linalg.qr` for pytorch > `v1.9.0` 2021-06-23 13:49:42 +02:00
Eren Gölge aba840b4e6 Fix loading the `amp` scaler from a checkpoint 🛠️ 2021-06-23 13:49:42 +02:00
Eren Gölge 18e5393f16 Add 🐍 python 3.9 to CI 2021-06-23 13:49:36 +02:00
Eren Gölge 0ff2d2336a Fix wrong argument name 🛠️ 2021-06-22 16:21:11 +02:00
Eren Gölge 61c3cb871f Docstring edit in `TTSDataset.py` ✍️ 2021-06-22 16:21:11 +02:00
Eren Gölge 6f739ea07a Fix `eval_log` for `gan.py` 🛠️ 2021-06-22 16:21:11 +02:00
Eren Gölge ebb91c0fbb Move `TorchSTFT` to `utils.audio` 2021-06-22 16:21:11 +02:00
Eren Gölge 01c4b22a2f Fixup `trainer.py` 🛠️ 2021-06-22 16:21:11 +02:00
Eren Gölge 7de2756fc4 Enable support for 🐍 python 3.10 
Bump up versions numpy 1.19.5 and TF 2.5.0
 2021-06-22 16:21:11 +02:00
Eren Gölge 220e184f66 Apply small fixes for API compatibility 2021-06-22 16:21:11 +02:00
Eren Gölge 77d57dd301 Print `max_decoder_steps` when model reaches the limit 2021-06-22 16:21:11 +02:00
Eren Gölge 7dc2177df4 Update `synthesizer` for speaker and model init 2021-06-22 16:21:11 +02:00
Eren Gölge c3a0bc702e fixup configs 2021-06-22 16:21:11 +02:00
Eren Gölge 0e01c2594f Update `speaker_manager` 2021-06-22 16:21:11 +02:00
Eren Gölge 8182f5168f Fixup `utils` for the trainer 2021-06-22 16:21:11 +02:00
Eren Gölge b4bb567e04 Update `vocoder` utils 2021-06-22 16:21:11 +02:00
Eren Gölge f3ff5b1971 Update `TTS.bin` scripts for the new API 2021-06-22 16:21:11 +02:00
Eren Gölge aed919cf1c Update `vocoder` datasets and `setup_dataset` 2021-06-22 16:21:11 +02:00
Eren Gölge 59abf490a1 Implement `setup_model` for vocoder models 2021-06-22 16:21:11 +02:00
Eren Gölge 420820caf4 Update vocoder models 2021-06-22 16:21:11 +02:00
Eren Gölge d10f9c5676 Update `tts.models.setup_model` 2021-06-22 16:21:11 +02:00
Eren Gölge cae702980f Create base 🐸TTS model abstraction for tts models 2021-06-22 16:21:11 +02:00
Eren Gölge 70d968b169 Update vocoder model configs 2021-06-22 16:21:11 +02:00
Eren Gölge f8a3460818 Update tts model configs 2021-06-22 16:21:11 +02:00
Eren Gölge acd96a4940 Implement unified IO utils 2021-06-22 16:21:10 +02:00
Eren Gölge 6b907554f8 Implement unified trainer 2021-06-22 16:21:10 +02:00
Eren Gölge 20c4a8c8e1 `tts` model abstraction with `TTSModel` 2021-06-22 16:21:10 +02:00
Eren Gölge b934665fc0 fix calculation of `loader_start_time` 2021-06-22 16:21:10 +02:00
Eren Gölge 64f0f57757 `TrainerAbstract` and related updates for `TrainerTTS` 2021-06-22 16:21:10 +02:00
Eren Gölge f077a356e0 rename to 2021-06-22 16:21:10 +02:00
Eren Gölge 4575b70826 merge if branches with the same implementation 2021-06-22 16:21:10 +02:00
Eren Gölge 59be1b9af1 adjust `distribute.py` for the `train_tts.py` 2021-06-22 16:21:10 +02:00
Eren Gölge 614738cc85 downsize melgan test model size 2021-06-22 13:12:52 +02:00
Eren Gölge 4f29725eb6 fix glow-tts `inference()` 2021-06-22 13:12:52 +02:00
Eren Gölge a87c886497 refactor and fix multi-speaker training in Trainer and Tacotron models 2021-06-22 13:12:52 +02:00
Eren Gölge 0206bb847b add max_decoder_steps argument to tacotron models 2021-06-22 13:12:52 +02:00
Eren Gölge cbb52b3d83 fix speaker_manager init 2021-06-22 13:12:52 +02:00
Eren Gölge d2fd6a34a1 use get_speaker_manager in Trainer and save speakers.json file when 
needed
 2021-06-22 13:12:52 +02:00
Eren Gölge 147550c65f make style and linter fixes 2021-06-22 13:12:52 +02:00
Eren Gölge a605dd3d08 Compute d_vectors and speaker_ids separately in TTSDataset 2021-06-22 13:12:52 +02:00
Eren Gölge f00ef90ce6 rename external speaker embedding arguments as `d_vectors` 2021-06-22 13:12:52 +02:00
Eren Gölge e7b7268c43 use `to_cuda()` for moving data in `format_batch()` 2021-06-22 13:12:52 +02:00
Eren Gölge 26a3312f0d change `to(device)` to `type_as` in models 2021-06-22 13:12:52 +02:00
Eren Gölge c09622459e init `durations = None` 2021-06-22 13:12:52 +02:00
Eren Gölge 2e31659dd9 docstring fix 2021-06-22 13:12:52 +02:00
Eren Gölge 7a0750a4f5 make style 2021-06-22 13:12:52 +02:00
Eren Gölge 534401377d styling formatting.py 2021-06-22 13:12:52 +02:00
Eren Gölge e229f5c081 fix type annotations 2021-06-22 13:12:52 +02:00
Eren Gölge 506189bdee update glow-tts output shapes to match [B, T, C] 2021-06-22 13:12:52 +02:00
Eren Gölge f568833d28 formating `cond_input` with a function in Tacotron models 2021-06-22 13:12:52 +02:00
Eren Gölge 254707c610 update imports for `formatters` 2021-06-22 13:12:52 +02:00
Eren Gölge 223502d827 fix glow-tts inference and forward functions for handling `cond_input` 
and refactor its test
 2021-06-22 13:12:52 +02:00
Eren Gölge d4b1acfa81 refactor `SpeakerManager` 2021-06-22 13:12:52 +02:00
Eren Gölge 26e7c0960c linter fixes 2021-06-22 13:12:52 +02:00
Eren Gölge 79f7c5da1e delete separate tts training scripts and pre-commit configuration 2021-06-22 13:12:52 +02:00
Eren Gölge ca787be193 make style 2021-06-22 13:12:52 +02:00
Eren Gölge d376647ca0 `logging/__init__.py` 2021-06-22 13:12:52 +02:00
Eren Gölge bb58a0588e fix logger imports 2021-06-22 13:12:52 +02:00
Eren Gölge 9bbc924377 import missings 2021-06-22 13:12:52 +02:00
Eren Gölge b4d4ce0d7e remove redundant imports 2021-06-22 13:12:52 +02:00
Eren Gölge aefa71155c make style 2021-06-22 13:12:52 +02:00
Eren Gölge 88d8a94a10 update extract_tts_spectrogram for `cond_input` API of the models 2021-06-22 13:12:52 +02:00
Eren Gölge 667bb708b6 update `extract_tts_spec...` using `SpeakerManager` 2021-06-22 13:12:52 +02:00
Eren Gölge 830306d2fd update `extract_tts_spectrograms` for the new model API 2021-06-22 13:12:52 +02:00
Eren Gölge c673eb8ef8 correct import of `load_meta_data` 
remove redundant import
 2021-06-22 13:12:52 +02:00
Eren Gölge f0a419546b fix `Synthesized` for the new `synthesis()` 2021-06-22 13:12:52 +02:00
Eren Gölge c7ff175592 revert logging.info to print statements for trainer 2021-06-22 13:12:52 +02:00
Eren Gölge fd6afe5ae5 update `setup_model.py` imports 2021-06-22 13:12:52 +02:00
Eren Gölge c82d91051d update align_tts.py model for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge 4f66e816d1 update align_tts_loss for trainer 2021-06-22 13:12:52 +02:00
Eren Gölge 8213ad8b5f update aling_tts_config for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge 8dfd4c91ff update trainer.py for better logging handling, restoring models and 
rename init_ functions with get_
 2021-06-22 13:12:52 +02:00
Eren Gölge fb9289d365 update `synthesis.py` for being more generic 2021-06-22 13:12:52 +02:00
Eren Gölge f121b0ff5d update `speedy_speech.py` model for trainer 2021-06-22 13:12:52 +02:00
Eren Gölge 843b3ba960 update `speedy_speecy_config.py` for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge c9790bee2c update tacotron model to return `model_outputs` 2021-06-22 13:12:52 +02:00
Eren Gölge f09ec7e3a7 update glow-tts for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge 3346a6d9dc update `sequence_mask` import globally 2021-06-22 13:12:52 +02:00
Eren Gölge 9765b1aa6b update `glow_tts_config.py` for setting the optimizer and the scheduler 2021-06-22 13:12:52 +02:00
Eren Gölge 6bf6543df8 typing annotation for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge 57cdddef16 add trainer and train_tts 2021-06-22 13:12:52 +02:00
Eren Gölge d769af9e3b remove `truncated` from synthesizer 2021-06-22 13:12:52 +02:00
Eren Gölge 570633ab80 update console logger 2021-06-22 13:12:52 +02:00
Eren Gölge 2ac6b824ca update `synthesis.py` for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge c9e5527070 remove `tts.generic_utils` as all the functions are moved to other files 2021-06-22 13:12:52 +02:00
Eren Gölge 2ab723cd10 update Tacotron models for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge d6b6a15b5c add `gradual_training` argument to tacotron.py 2021-06-22 13:12:52 +02:00
Eren Gölge 118a7f2b43 import missings for tacotron.py 2021-06-22 13:12:52 +02:00
Eren Gölge c98149d488 mode `setup_model()` to `models/__init__.py` 2021-06-22 13:12:52 +02:00
Eren Gölge 86edf6ab0e add sequence_mask to `utils.data` 2021-06-22 13:12:52 +02:00
Eren Gölge c61486b1e3 `setup_loss()` in `layer/__init__.py` 2021-06-22 13:12:52 +02:00
Eren Gölge f07209d2e0 rename preprocess.py -> formatters.py 2021-06-22 13:12:52 +02:00
Eren Gölge facb782851 move load_meta_data and related functions to `datasets/__init__.py` 2021-06-22 13:12:52 +02:00
Eren Gölge b9d4355d20 set test_sentences in config 2021-06-22 13:12:52 +02:00
Eren Gölge 7bdd0eb72f trainer-API updates 2021-06-22 13:12:52 +02:00
Eren Gölge 0f284841d1 rename MyDataset -> TTSDataset 2021-06-22 13:12:52 +02:00
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
Adam Froghyar b0aa189348 Forcing do_trim_silence to False in the extract TTS script 2021-06-14 10:44:00 +02:00
Eren Gölge d245b5d48f bump up v0.0.15.1 2021-06-08 09:21:01 +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 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 49c5e5d820 maket style japanese PR 2021-06-02 11:44:46 +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
Katsuya Iida 6d8310d2a9 Set the version to the same with the dev branch. 2021-06-02 07:48:28 +09:00
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 bec85ac58d make style 2021-05-31 16:37:15 +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
Edresson 7448177b72 use SpeakerManager on compute embeddings script 2021-05-29 21:11:53 -03:00
Katsuya Iida c4a5a73f18 update Kokoro config 2021-05-29 19:17:27 +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
Edresson 825734a3a9 remove unused embeddings export 2021-05-27 19:10:24 -03:00
Katsuya Iida c4987e9d4e Move import at the head of the file. 2021-05-28 00:22:57 +09:00
Eren Gölge 925c08cf95 replace unidecode with anyascii 2021-05-27 14:02:44 +02:00
Eren Gölge e08c58db3b bump up version to v0.14.1 2021-05-27 13:11:01 +02:00
Eren Gölge c6f22aaa67 fix #509 2021-05-27 13:09:15 +02:00
Edresson 1496f271dc update Compute embeddings script 2021-05-27 00:45:18 -03:00
Edresson bc5307caa0 add unit tests for SoftmaxAngleProtoLoss and ResnetSpeakerEncoder and bugfix 2021-05-26 20:35:58 -03:00
Edresson c90037c2e9 solve merge problems 2021-05-26 16:01:30 -03:00
Katsuya Iida f921a05bdb Fixed lint errors 2021-05-26 19:02:16 +09:00
Edresson Casanova f89cb6aec2
Merge branch 'dev' into dev 2021-05-25 17:30:25 -03:00
Edresson d570c2d790 pylint fix and data loader bug fix 2021-05-26 01:11:37 -03:00
Katsuya Iida 0536aa6d0f Japanese Tacotron 2 model 2021-05-22 17:12:19 +09:00
Eren Gölge 5482a0f62d type def for gradual_training 2021-05-19 14:03:26 +02:00
Eren Gölge df6a98d0c3 type def for gradual_training 2021-05-19 14:00:44 +02:00
Eren Gölge 16576d6408 bump version number 2021-05-19 12:35:10 +02:00
Eren Gölge 8a7c40736c set use_phonemes false 2021-05-19 01:27:26 +02:00
Eren Gölge ccfaa6b1d5 add `needs_phonemizer` field to models.json. If set true these models 
are only compatible with v0.0.13 or below.
 2021-05-18 17:57:28 +02:00
Eren Gölge a14fcf2a13 remove text_processing test 2021-05-18 17:57:28 +02:00
Eren Gölge d7fae3f515 remove all espeaker and phonemizer deps 2021-05-18 17:57:28 +02:00
Eren Gölge ced05e812a move chinese phonemizer 2021-05-18 17:57:28 +02:00
Eren Gölge 218af1d9a2 change `list` to `List` in config 2021-05-18 17:30:27 +02:00
Eren Gölge 4df31f7fbd unused_speakers argument for ignoring speaker ids in multi-speaker 
training
 2021-05-18 14:50:03 +02:00
Eren Gölge c2c7dff805 use relaxted coqpit parser 2021-05-18 14:49:47 +02:00
Edresson 856ea19758 bug fix in dataloader and update inference 2021-05-18 03:43:16 -03:00
Eren Gölge d1b469935d tacotron DDC LJSpeech recipe 2021-05-17 11:42:14 +02:00
Eren Gölge 34a42d379f update tacotron_config.py for checking `r` and the docstring 2021-05-17 11:35:30 +02:00
Eren Gölge 12722501bb styling 2021-05-15 23:48:31 +02:00
Eren Gölge 8b1014d188 add docstrings with default value fixes 2021-05-15 23:45:10 +02:00
Eren Gölge da49089a72 update melgan training test batch size 2021-05-12 10:12:11 +02:00
Edresson 3433c2f348 add compute embedding for the new speaker encoder 2021-05-12 03:06:46 -03:00
Eren Gölge 0213e1cbf4 update configs for tts models to match the field typed with the expected 
values
 2021-05-12 00:57:38 +02:00
Eren Gölge 715b0a65a0 update main.yml for python x64 
fix test
 2021-05-12 00:57:29 +02:00
Edresson 3fcc748b2e implement the Speaker Encoder H/ASP 2021-05-11 16:27:05 -03:00
Eren Gölge 843d1b3d98 linter fixes 2021-05-11 11:30:00 +02:00
Eren Gölge 19fb1d743d style update 2021-05-11 11:30:00 +02:00
Eren Gölge 6e980b49c4 fix synthesizer.py for Coqpit 2021-05-11 11:29:18 +02:00
Eren Gölge db14dcd95a remove old load_config 2021-05-11 11:29:18 +02:00
Eren Gölge a21ac883dd add get_cuda() 2021-05-11 11:29:18 +02:00
Eren Gölge 21dd4d7960 fix load_config imports for Coqpit 2021-05-11 11:29:18 +02:00
Eren Gölge c57f0b46bb reintro use_gst for backwars compat 2021-05-11 11:29:18 +02:00
Eren Gölge 18e76a2309 fix speaker encoder model initialization 2021-05-11 11:29:18 +02:00
Eren Gölge 10de40bba1 make num_workers mandatory config field 2021-05-11 11:29:18 +02:00
Eren Gölge df1ddd3539 allow read_json_with_comments for backward compat 2021-05-11 11:29:18 +02:00
Eren Gölge 9f7599e3c3 fix train_encoder for coqpit 2021-05-11 11:29:18 +02:00
Eren Gölge f8e52965dd add speaker encoder coqpit 2021-05-11 11:29:18 +02:00
Eren Gölge ce2bba543e remove extra from utils and move funcs to io.py 2021-05-11 11:29:18 +02:00
Eren Gölge 812dbc2b06 rm config.json 2021-05-11 11:29:18 +02:00
Eren Gölge 3fde2001b1 train_encoder refactoring for coqpit 2021-05-11 11:29:18 +02:00
Eren Gölge 9ee70af9bb code styling 2021-05-11 11:29:18 +02:00
Eren Gölge 10db2baa06 global shared Coqpit configs 2021-05-11 11:29:18 +02:00
Eren Gölge 3dec62b183 add Coqpits for the vocoder models 2021-05-11 11:29:18 +02:00
Eren Gölge 6f4eed94f5 remove *.json vocoder configs 2021-05-11 11:29:18 +02:00
Eren Gölge 78b3825d0b update train scripts for coqpit 2021-05-11 11:29:18 +02:00
Eren Gölge 757e90b1cc load_config function to initialize the right Coqpit for the given model 2021-05-11 11:29:18 +02:00
Eren Gölge e6f45b9eb7 update train_vocoder_gan.py for coqpit 2021-05-11 11:29:18 +02:00
Eren Gölge bcebd69d09 remove bash tts training tests 2021-05-11 11:29:17 +02:00
Eren Gölge 7663bc63c1 add Coqpit configs for the TTS models 2021-05-11 11:29:17 +02:00
Eren Gölge 7227e8f1d2 update train_align_tts.py for coqpit 2021-05-11 11:29:17 +02:00
Eren Gölge 51a7e06945 glow_tts_config.py and train test on python 2021-05-11 11:29:17 +02:00
Eren Gölge 720fe13056 update glow_tts modules and training script for coqpit use 2021-05-11 11:29:17 +02:00
Eren Gölge 816e7ee698 remove default configs.json as replacing with Coqpit configs 2021-05-11 11:29:17 +02:00
Eren Gölge 35341d5482 move bash script based tests to python with coqpit 2021-05-11 11:29:17 +02:00
Eren Gölge 647163397d coqpit refactoring 2021-05-11 11:29:17 +02:00
Eren Gölge eaa130e813 fix tacotron for coqpit 2021-05-11 11:29:17 +02:00
Eren Gölge 65d7ad4250 refactor train_speedy_speech.py for coqpit 2021-05-11 11:29:17 +02:00
Eren Gölge 4a58fdfd59 comment out check-arguments before copying fields to the configs 2021-05-11 11:29:17 +02:00
Eren Gölge 05d9543ed8 init GST module using gst config in Tacotron models 2021-05-11 11:29:17 +02:00
Eren Gölge 93a00373f6 move split_dataset 2021-05-11 11:29:17 +02:00
Eren Gölge 9c18e40f64 black formatting 2021-05-11 11:29:17 +02:00
Eren Gölge c34c8137d7 update compute_statistics for coqpit 2021-05-11 11:29:17 +02:00
Eren Gölge 79d7215142 config refactor #5 WIP 2021-05-11 11:29:17 +02:00
Eren Gölge dc50f5f0b0 config refactor #4 WIP 2021-05-11 11:28:35 +02:00
Eren Gölge 97bd5f9734 [ci skip] config update #3 WIP 2021-05-11 11:28:35 +02:00
Eren Gölge a21c0b5585 config update 2 WIP 2021-05-11 11:28:35 +02:00
Eren Gölge e092ae40dc config update WIP 2021-05-11 11:28:35 +02:00
Eren Gölge 06f80a4806 update check argument 2021-05-11 11:28:35 +02:00
Eren Gölge bf7ddfa542
Merge pull request #481 from chmodsss/main 
Accessing __version__ command
 2021-05-11 10:20:48 +02:00
Edresson 85ccad7e0a add Audio data augamentation Addtive and RIR 2021-05-11 00:59:57 -03:00
Edresson 77d85c6cc5 add softmaxproto loss and bug fix in data loader 2021-05-10 17:08:38 -03:00
chmodsss 607d5cf377 [#480] Adding version variable 2021-05-10 19:46:34 +02:00
Adam Froghyar 7ddc885f37 deleted a line the broke GravesAttention 2021-05-10 15:42:59 +02:00
Edresson 78bad25f2b update voxceleb download link 2021-05-07 23:45:15 -03:00
Eren Gölge f7582107da
Merge pull request #453 from Edresson/dev 
Script for spectrogram extraction using teacher forcing and Glow-TTS inference with MAS.
 2021-05-06 17:53:28 +02:00
Edresson 501c8e0302 remove unused vars on extract tts spectrograms script 2021-05-04 19:04:13 -03:00
Eren Gölge 0325c58862
Merge pull request #468 from shaun95/patch-1 
Update losses.py
 2021-05-03 14:45:24 +02:00
Eren Gölge 8cb27267a4 formatting 2021-05-03 14:26:35 +02:00
Eren Gölge 87d674a038 bumpup librosa version to 0.8.0 2021-05-03 14:25:09 +02:00
shaun 7d0ec62bf1
Update losses.py 
The block of code for use_l1_spec_loss is repeated which doubles the amount of L1 loss when enabled.
The weight for L1 loss in hifigan_ljspeech configutation will likely need to be doubled to compensate (l1_spec_loss_weight)
 2021-05-02 14:14:24 +02:00
Edresson 3ecd556bbe add unit test for extract tts spectrograms script 2021-05-01 13:41:56 -03:00
Edresson 446b1da936 create inference function 2021-04-29 18:18:37 -03:00
Eren Gölge f02f0338c2 fix .models.json and add testing to check released models availability 2021-04-29 09:32:36 +02:00
Eren Gölge fd95e9b8a4 [ci skip] Add sam models 2021-04-28 21:57:31 +02:00
Agrin Hilmkil 351d0ed6ae Remove unnecessary fsspec usage 2021-04-28 11:21:08 +02:00
Agrin Hilmkil 167f86417e Move dev, tf, notebook dependencies to extras 2021-04-28 11:20:06 +02:00
Eren Gölge 1235e54738 test for synthesize.py 2021-04-27 14:17:38 +02:00
Eren Gölge 4719414f2e remove imports 2021-04-27 11:25:17 +02:00
Eren Gölge add97cddc1 move function and remove import 2021-04-27 11:22:56 +02:00
Eren Gölge 734e6a515c bug fix 2021-04-27 10:27:45 +02:00
Eren Gölge 6bdd81667e place holders for sc-glow and hifigan models 2021-04-26 19:53:12 +02:00
Eren Gölge 2f0716073e enable multi-speaker CoquiTTS models for synthesize.py 2021-04-26 19:36:53 +02:00
Eren Gölge b531fa699c remove conflicy noise 2021-04-26 15:27:52 +02:00
Eren Gölge f37b488876 Merge branch 'speaker-manager' of https://github.com/coqui-ai/TTS into speaker-manager 2021-04-26 15:25:25 +02:00
Eren Gölge b82daa5e86 style and linter fixes 2021-04-26 15:22:24 +02:00
Edresson 20e42a3381 add save audio option 2021-04-23 15:00:00 -03:00
Edresson 8228091f92 add script for extraction of tts spectrograms 2021-04-23 14:17:46 -03:00
Eren Gölge 4cf211348d styling and linting 2021-04-23 18:04:37 +02:00
Eren Gölge 7eb0c60d2e let synthesizer to pass speaker encoder file paths to speaker manager 2021-04-23 18:04:37 +02:00
Eren Gölge f69195739e let speaker manager compute mean x_vector from multiple wav files 2021-04-23 18:04:37 +02:00
Eren Gölge 179722e3a7 new arguments to synthesize.py for loading speaker encoder and speaker wavs 2021-04-23 18:04:37 +02:00
Eren Gölge dfa415a8b8 small refactor in server.py 2021-04-23 18:04:37 +02:00
Eren Gölge c80d21f311 load speaker_encoder_ap and compute x_vector directly from the input file in speaker manager 2021-04-23 18:04:37 +02:00
Eren Gölge ad047c8195 html formatting, enable multi-speaker model on the server with a dropdown menu to select the speaker 2021-04-23 18:04:37 +02:00
Eren Gölge f9f3d04d14 remove moved function 2021-04-23 18:04:37 +02:00
Eren Gölge 10c988ac8c update server.py 2021-04-23 18:04:37 +02:00
Eren Gölge 6d0f5e0459 use SpeakerManager in Synthesizer 2021-04-23 18:04:37 +02:00
Eren Gölge e97126314c add ```unique``` argument to make_symbols to fix the incompat. issue of the 
SC-Glow models
 2021-04-23 18:04:37 +02:00
Eren Gölge d08888e603 formating speakers.py 2021-04-23 18:04:37 +02:00
Eren Gölge df422223a3 initial SpeakerManager implementation 2021-04-23 18:04:37 +02:00
Eren Gölge 7a7aeb35f5 fix the glow-tts in setup_model 2021-04-23 18:04:37 +02:00
Eren Gölge d42748082a update argument name external_speaker_embedding_dim -> speaker_embedding_dim 
add inference_noise_scale argument to glow-tts
 2021-04-23 18:04:37 +02:00
Eren Gölge 2da81f5bb6 add load_chekpoint to speaker encoder 2021-04-23 18:04:37 +02:00
Eren Gölge 1229ccbf07 update argument name in server.py 2021-04-23 18:04:37 +02:00
Eren Gölge af2d36faeb update synthesize.py for multi-speaker setting 2021-04-23 18:04:37 +02:00
Eren Gölge 99dc07a7dd add ```unique``` param to keep scglow models compatible (they are duplicate symbols ins the character set) 2021-04-23 18:04:37 +02:00
Eren Gölge c955a12428 set the default layer size compatible with scglow 2021-04-23 18:04:37 +02:00
Eren Gölge 3ace2440fa fix a mistake from rebase 2021-04-23 18:04:37 +02:00
Eren Gölge aadb2106ec code styling 2021-04-23 18:04:37 +02:00
Eren Gölge af7baa3387 refactoring to allow defining the speaker file externally 2021-04-23 18:04:37 +02:00
kirianguiller 7dccbfdcd5 handle multi speaker and gst in Synthetizer class 2021-04-23 18:04:37 +02:00
Edresson d2b6326b8b change optimizer initialization for compatibility with Hifi-GAN official implementation 2021-04-23 07:54:39 -03:00
WeberJulian 4205284f92
Change name of the functions 2021-04-23 10:09:55 +02:00
WeberJulian a26498181b Change back the default value 2021-04-22 16:10:17 +02:00
Julian Weber 355e1f47ab fix dumb mistake 2021-04-22 15:50:29 +02:00
Julian Weber c125b71f36 fix windows support 2021-04-22 15:14:24 +02:00
Jörg Thalheim f5fd7f78d4 server: also listen to ipv6 
The [::] address will listen to both ipv4/ipv6 addresses.
 2021-04-22 12:38:55 +02:00
Eren Gölge ef37633cb3 [ci skip] use prenet_dropout by default with Tacotron models 2021-04-22 12:38:55 +02:00
Eren Gölge e1d960da9e use SpeakerManager in Synthesizer 2021-04-21 13:13:27 +02:00
Eren Gölge 04b6881b66 add ```unique``` argument to make_symbols to fix the incompat. issue of the 
SC-Glow models
 2021-04-21 13:12:35 +02:00
Eren Gölge 790946faec formating speakers.py 2021-04-21 13:12:11 +02:00
Eren Gölge ab313814de initial SpeakerManager implementation 2021-04-21 13:11:46 +02:00
Eren Gölge 09890c7421 fix the glow-tts in setup_model 2021-04-21 13:10:40 +02:00
Eren Gölge 8764d02eb2 update argument name external_speaker_embedding_dim -> speaker_embedding_dim 
add inference_noise_scale argument to glow-tts
 2021-04-21 13:09:44 +02:00
Eren Gölge 8b40720977 add load_chekpoint to speaker encoder 2021-04-21 13:09:04 +02:00
Eren Gölge 37cad38c27 update argument name in server.py 2021-04-21 13:08:45 +02:00
Eren Gölge 9bccee9da8 update synthesize.py for multi-speaker setting 2021-04-21 13:08:25 +02:00
Eren Gölge d2fa8add1f add ```unique``` param to keep scglow models compatible (they are duplicate symbols ins the character set) 2021-04-16 19:40:13 +02:00
Eren Gölge d9612a4351 set the default layer size compatible with scglow 2021-04-16 19:40:13 +02:00
Eren Gölge 1038fd420d fix a mistake from rebase 2021-04-16 19:39:47 +02:00
Eren Gölge 47e356cb48 code styling 2021-04-16 16:01:40 +02:00
Eren Gölge 25328aad00 refactoring to allow defining the speaker file externally 2021-04-16 15:59:57 +02:00
kirianguiller 48ae52a9a3 handle multi speaker and gst in Synthetizer class 2021-04-16 15:54:49 +02:00
Eren Gölge a53958ae3a fix urls for the new models 2021-04-15 17:05:00 +02:00
Eren Gölge 9cc17be53a formatting and a small bug fix in Tacotron model 2021-04-15 16:36:51 +02:00
Eren Gölge 1ad838bc83 add newly released models under .model.json 2021-04-15 16:06:10 +02:00
Eren Gölge 7cada1a949 remove noise 2021-04-15 15:30:45 +02:00
Eren Gölge d60a8d7211 show the real waveform on TB too for GAN vocoder training. 2021-04-15 15:30:06 +02:00
Eren Gölge 5fbe926429 change the default TTS model to TacotronDDC 2021-04-15 15:29:44 +02:00
Eren Gölge 3de5a89154 optionally enable prenet dropout at inference time for tacotron models 2021-04-13 13:24:56 +02:00
Eren Gölge 28a2fed8a3 update hifigan in .model.json 2021-04-12 16:48:05 +02:00
Eren Gölge abaf36861a aligntts model .model.json placeholder 2021-04-12 16:43:52 +02:00
Eren Gölge 480e2f7888 docstring update and better handling make_symbols 2021-04-12 16:40:49 +02:00
Eren Gölge b735076bb4 linter fixes 2021-04-12 13:14:11 +02:00
Eren Gölge b11d1cb845 small fixes 2021-04-12 12:40:55 +02:00
Eren Gölge a7f6045644 Merge branch 'reformat' into hifigan-reformat 2021-04-12 12:00:17 +02:00
Eren Gölge f519012dea reformatting and styling 2021-04-12 11:47:39 +02:00
Eren Gölge 9011dddf77 tacotron DDC placeholder in models.json 2021-04-12 04:06:27 +02:00
Eren Gölge d295d5de97 remove torch.no_grad from TorchSTFT 2021-04-10 19:43:57 +02:00
Eren Gölge 5b70da2e3f restore schedulers only if training is continuing a previous training 
inherit nn.Module for TorchSTFT
 2021-04-09 19:31:28 +02:00
Eren Gölge 2c71c6d8cd [ci skip]update gan vocoder configs to reflect the recent changes 2021-04-09 17:15:32 +02:00
Eren Gölge 2b529f60c8 update default hifigan config 2021-04-09 11:40:06 +02:00
Eren Gölge 105e0b4d62 vocoder gan training fixes 2021-04-09 11:38:04 +02:00
Eren Gölge 87ee6ceb57 style update #3 2021-04-09 01:17:15 +02:00
Eren Gölge 18d9ec8036 format with black 2021-04-09 00:54:59 +02:00
Eren Gölge e5b9607bc3 isort all imports 2021-04-09 00:45:20 +02:00
Eren Gölge 0e79fa86ad format with black and pylint 2.7.3 2021-04-09 00:38:08 +02:00
Eren Gölge cd69da4868 linter fixes #2 2021-04-08 16:57:46 +02:00
Eren Gölge 4d3e1e9d9a linter fix 2021-04-08 14:57:46 +02:00
Eren Gölge 53f54898bc small fixes 2021-04-08 14:22:47 +02:00
Eren Gölge 006b1d3aaa bug fix 2021-04-08 13:17:45 +02:00