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
4,407 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

332 Commits

Author SHA1 Message Date
Eren Gölge 49bac724c0
Implement VitsAudioConfig (#1556) 
* Implement VitsAudioConfig

* Update VITS LJSpeech recipe

* Update VITS VCTK recipe

* Make style

* Add missing decorator

* Add missing param

* Make style

* Update recipes

* Fix test

* Bug fix

* Exclude tests folder

* Make linter

* Make style
 2022-07-12 18:49:58 +02:00
a-froghyar 34b80e0280
feat: updated recipes and lr fix (#1718) 
- updated the recipes activating more losses for more stable training
- re-enabling guided attention loss
- fixed a bug about not the correct lr fetched for logging
 2022-07-12 15:00:53 +02:00
Eren G??lge 3328be7a8e Remove GL message 2022-06-21 12:39:31 +02:00
p0p4k 71281ff1e4
Add support for model_info in CLI (#1623) 
* model_info

* model_info

* model_info_by_idx and name

* model_info_by_idx and name

* model_info

* Update manage.py

* fixed linter

* fixed linter

* fixed linter

* fixed linter

* fixed return style checks

* fixed linter

* fixed linter

* fixed idx always positive

* added comments

* fix parser.args check

* fix parser.args check

* Make style

Co-authored-by: Eren G??lge <egolge@coqui.ai>
 2022-06-20 23:28:17 +02:00
a-froghyar 8be21ec387
Capacitron (#977) 
* new CI config

* initial Capacitron implementation

* delete old unused file

* fix empty formatting changes

* update losses and training script

* fix previous commit

* fix commit

* Add Capacitron test and first round of test fixes

* revert formatter change

* add changes to the synthesizer

* add stepwise gradual lr scheduler and changes to the recipe

* add inference script for dev use

* feat: add posterior inference arguments to synth methods
- added reference wav and text args for posterior inference
- some formatting

* fix: add espeak flag to base_tts and dataset APIs
- use_espeak_phonemes flag was not implemented in those APIs
- espeak is now able to be utilised for phoneme generation
- necessary phonemizer for the Capacitron model

* chore: update training script and style
- training script includes the espeak flag and other hyperparams
- made style

* chore: fix linting

* feat: add Tacotron 2 support

* leftover from dev

* chore:rename parser args

* feat: extract optimizers
- created a separate optimizer class to merge the two optimizers

* chore: revert arbitrary trainer changes

* fmt: revert formatting bug

* formatting again

* formatting fixed

* fix: log func

* fix: update optimizer
- Implemented load_state_dict for continuing training

* fix: clean optimizer init for standard models

* improvement: purge espeak flags and add training scripts

* Delete capacitronT2.py

delete old training script, new one is pushed

* feat: capacitron trainer methods
- extracted capacitron specific training  operations from the trainer into custom
methods in taco1 and taco2 models

* chore: renaming and merging capacitron and gst style args

* fix: bug fixes from the previous commit

* fix: implement state_dict method on CapacitronOptimizer

* fix: call method

* fix: inference naming

* Delete train_capacitron.py

* fix: synthesize

* feat: update tests

* chore: fix style

* Delete capacitron_inference.py

* fix: fix train tts t2 capacitron tests

* fix: double forward in T2 train step

* fix: double forward in T1 train step

* fix: run make style

* fix: remove unused import

* fix: test for T1 capacitron

* fix: make lint

* feat: add blizzard2013 recipes

* make style

* fix: update recipes

* chore: make style

* Plot test sentences in Tacotron

* chore: make style and fix import

* fix: call forward first before problematic floordiv op

* fix: update recipes

* feat: add min_audio_len to recipes

* aux_input["style_mel"]

* chore: make style

* Make capacitron T2 recipe more stable

* Remove T1 capacitron Ljspeech

* feat: implement new grad clipping routine and update configs

* make style

* Add pretrained checkpoints

* Add default vocoder

* Change trainer package

* Fix grad clip issue for tacotron

* Fix scheduler issue with tacotron

Co-authored-by: Eren Gölge <egolge@coqui.ai>
Co-authored-by: WeberJulian <julian.weber@hotmail.fr>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
 2022-05-20 16:17:11 +02:00
Edresson Casanova ee99a6c1e2 Fix voice conversion inference (#1583) 
* Add voice conversion zoo test

* Fix style

* Fix unit test
 2022-05-20 15:50:25 +02:00
Eren Gölge 2fc38f67d2 Update SpeakerManager init in Synthesizer 2022-05-11 11:32:27 +02:00
Edresson Casanova 8d228ab22a
Trick to Upsampling to High sampling rates using VITS model (#1456) 
* Add upsample VITS support

* Fix the bug in inference

* Fix lint checks

* Add RMS based norm in save_wav method

* Style fix

* Add the period for VITS multi-period discriminator in model_args

* Bug fix in speaker encoder load in inference time

* Add unit tests

* Remove useless detach_z_vocoder parameter

* Add docs for VITS upsampling

* Fix the docs

* Rename TTS_part_sample_rate to encoder_sample_rate

* Add upsampling_init and upsampling_z methods

* Add asserts for encoder_sample_rate part

* Move upsampling tests to test_vits.py
 2022-04-26 11:47:46 +02:00
WeberJulian 30bea7d53c
Update manage.py (#1514) 2022-04-19 14:27:32 +02:00
Eren Gölge 7133f8f47d
Print Model's license when downloading (#1512) 
* Print model license while downloading

* Make style

* Add a new license link

* Make style
 2022-04-19 14:18:49 +02:00
Edresson Casanova 060e0f9368
Add EmbeddingManager and BaseIDManager (#1374) 2022-03-31 13:41:16 +02:00
WeberJulian 1b22f03e98
Fix G2P backend of the released models (#1461) 
* Fix enforce phonemizer

* Add new models

* Fix .model.json
 2022-03-30 12:47:11 +02:00
WeberJulian c66a6241fd
Enforce phonemizer definition for synthesis (#1441) 
* Enforce phonemizer definition for synthesis

* Fix train_tts, tokenizer init can now edit config

* Add small change to trigger CI pipeline

* fix wrong output path for one tts_test

* Fix style

* Test config overides by args and tokenizer

* Fix style
 2022-03-25 23:15:33 +01:00
Edresson Casanova 3435bc8fca Fix style tests 2022-03-23 15:05:32 -03:00
Edresson Casanova 0ae1e0248c Fix the bug for emptly audio files 2022-03-23 14:39:31 -03:00
Edresson Casanova ea53d6feb3 Replace webrtcvad by silero-vad 2022-03-23 14:39:31 -03:00
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
Eren Gölge 0870a4faa2
Make style (#1405) 2022-03-16 12:13:55 +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
Eren Gölge 942df0fb05 Update vits dataset 2022-03-02 09:14:32 +01:00
Eren Gölge 935a604046 Delete trainer_utils 2022-02-25 11:29:41 +01:00
Eren Gölge d0c27a9661 Update synthesis.py 2022-02-25 11:29:41 +01:00
Eren Gölge 2bad098625 Implement BaseVocabulary 2022-02-25 11:28:47 +01:00
Eren Gölge a013566d15 Delete trainer related code 2022-02-25 11:26:59 +01:00
Eren Gölge d5c0e17548 Load right char class dynamically 2022-02-25 11:26:59 +01:00
Eren Gölge 1f0c8179da Make style 2022-02-25 11:26:59 +01:00
Eren Gölge cd5d1497cf Add pitch_fmin pitch_fmax args to the audio 2022-02-25 11:26:59 +01:00
Eren Gölge 1445a46e9e Update synthesizer to use iinit_from_config 2022-02-25 11:26:59 +01:00
Eren Gölge 2fe16de8e3 Make lint 2022-02-25 11:25:00 +01:00
Eren Gölge 50e17097a7 Add verbose option to AudioProcessor 2022-02-25 11:24:13 +01:00
Eren Gölge c9972e6f14 Make lint 2022-02-25 11:07:34 +01:00
Eren Gölge 9bb347a52b Update for tokenizer API 2022-02-25 11:05:06 +01:00
Eren Gölge 84091096a6 Refactor Synthesizer class for TTSTokenizer 2022-02-25 11:05:06 +01:00
Eren Gölge 1df1d6c4a9 Update for tokenizer API 2022-02-25 10:48:03 +01:00
Eren Gölge 3476be30d7 Refactor Synthesizer class for TTSTokenizer 2022-02-25 10:48:03 +01:00
Eren Gölge 9397a56b13 Allow init_from_config from model or audio config 2022-02-25 10:48:03 +01:00
Eren Gölge acc6eef625 Update for tokenizer API 2022-02-25 10:48:02 +01:00
Eren Gölge 53f696615b Add init_from_config to AudioProcessor 2022-02-25 09:32:54 +01:00
Eren Gölge 3d86edfc81 Refactor Synthesizer class for TTSTokenizer 2022-02-25 09:32:54 +01:00
Eren Gölge 127118c637
Update TTS.tts formatters (#1228) 
* Return Dict from tts formatters

* Make style
 2022-02-11 23:03:43 +01:00
Eren Gölge fc09e319d4 Prioritize the given encoder path over config 2022-01-03 14:24:19 +00:00
Eren Gölge 7fad969a1f Fix if else statement 2022-01-03 14:16:11 +00:00
Eren Gölge e55f5ee59e Make linter 2022-01-01 15:50:04 +00:00
Eren Gölge 8fd1ee1926 Print urls when BadZipError 2022-01-01 15:26:35 +00:00
Eren Gölge 61874bc0a0 Fix your_tts inference from the listed models 2021-12-31 13:45:05 +00:00
Eren Gölge 5c5ddd2ba7 Init speaker manager for speaker encoder 2021-12-22 15:51:53 +00:00
Eren Gölge 633dcc9c56 Implement RMS volume normalization 2021-12-22 15:51:14 +00:00
Eren Gölge 56378b12f7 Fix speaker encoder init 2021-12-21 12:26:25 +00:00
Eren Gölge c9c1fa0548 Fix multi-speaker init in Synthesizer 2021-12-21 09:44:07 +00:00
Eren Gölge f769595112 Add more listing options to ModelManager 2021-12-20 11:54:10 +00:00
Eren Gölge 473414d4af Implement init_speaker_encoder and change arg names 2021-12-20 11:54:10 +00:00
Eren Gölge 35a781fb90 Fix synthesizer reading `use_language_embedding` 2021-12-20 11:54:10 +00:00
Eren Gölge 704dddcffa Make style 2021-12-20 11:54:10 +00:00
WeberJulian 54b7fb4e4a Fix zoo tests 2021-12-20 11:54:10 +00:00
WeberJulian a564eb9f54 Add support for multi-lingual models in CLI 2021-12-20 11:54:10 +00:00
Edresson 818dc4ccd8 Add Docstring for TorchSTFT 2021-12-20 11:54:10 +00:00
Edresson d39200e69b Remove torchaudio requeriment 2021-12-20 11:54:10 +00:00
Edresson 45d0b04179 Lint fixs 2021-12-20 11:54:10 +00:00
Edresson 2b2cecaea2 Set the new_fields in copy_model_files as None by default 2021-12-20 11:54:10 +00:00
Edresson 352aa69eca Create a module for the VAD script 2021-12-20 11:54:10 +00:00
loganhart420 103c010eca Add addtional datasets 2021-12-16 07:21:27 -05:00
Eren Gölge ce45d9e1af Make style and lint 2021-12-01 10:42:52 +00:00
Eren Gölge 512ada7548 Fix callbacks against multi-gpu training 2021-12-01 10:32:14 +00:00
Eren Gölge d227aaebcc Print when using Griffin-Lim in Synthesizer 2021-11-01 16:52:26 +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 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 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 1987aaaaed Update d-vector reshape in synthesizer 2021-10-21 13:53:25 +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 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 700b056117 Update Synthesizer multi-speaker handling 2021-10-15 10:21:12 +00:00
Eren Gölge 9a0d8fa027 Update `copy_model_files()` 2021-09-30 14:47:56 +00:00
Eren Gölge 8ada870a57 Refactor `trainer.py` for v2 2021-09-30 14:16:34 +00:00
Eren Gölge 7d8f77385a Use `glow-tts` in synthesis tests 2021-09-10 17:27:33 +00:00
Eren Gölge 742f9c54da Warn user if nan in GL 2021-09-10 08:26:05 +00:00
Eren Gölge 4761853c5c Fix imports 2021-09-08 13:34:40 +00:00
Eren Gölge 2c4bbbf9b9 Use pyworld for pitch 2021-09-06 15:16:58 +00:00
Eren Gölge 98a7271ce8 Refactor FastPitchv2 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 aacbb3ed77 Fix SpeakerManager usage in `synthesize.py` 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 d085642ac1 Cache pitch features 
Cache the features at the beginning of `BaseTTS` training.
 2021-09-06 15:16:58 +00:00
Eren Gölge fba257104d Compute F0 using librosa 2021-09-06 15:16:58 +00:00
Eren Gölge d16da949a5 Merge branch 'fix_distribute' into dev 2021-08-30 16:31:07 +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 18da8f5dbd Update pylint 2.10.2 and fix lint issues 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
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 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 537bc8487a Print model count when listing modelsk 2021-08-10 16:25:11 +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