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
4,471 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

351 Commits

Author SHA1 Message Date
Eren Gölge fcb0bb58ae
Handle when no batch sampler (#1882) 2022-08-18 11:26:04 +02:00
Eren Gölge bfc63829ac
Implement bucketed weighted sampling for VITS (#1871) 2022-08-15 11:08:11 +02:00
manmay nakhashi 7fd9b89ebf
fix get_random_embeddings --> get_random_embedding (#1726) 
* fix get_random_embeddings --> get_random_embedding

function typo leads to training crash, no such function

* fix typo

get_random_embedding
 2022-08-07 14:06:03 +02:00
ivan provalov 903d9c791a
Fix for FloorDiv Function Warning (#1760) 
* Fix for Floor Function Warning

Fix for Floor Function Warning

* Adding double quotes to fix formatting

Adding double quotes to fix formatting

* Update glow_tts.py

* Update glow_tts.py
 2022-07-20 11:31:22 +02:00
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
WeberJulian c614f21982
Add durations as aux input for VITS (#1694) 
* Add durations as aux input for VITS

* Make style

* Fix tts_tests

* Fix test_get_aux_input
 2022-07-12 14:25:21 +02:00
Eren Gölge f70e82cd19
Use fsspec and torch for embedding file IO (#1581) 
* Use fsspec and torch for embedding file

* Fixup

* Fix load and save files

* Fix compute embedding script

* Set use_cuda to true if available

* Add dummy speakers.pth file

* Make style

* Change default speakers file extension

Co-authored-by: WeberJulian <julian.weber@hotmail.fr>
 2022-06-01 13:49:42 +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
Edresson Casanova e5d8ec2402
Change the VITS upsampling interpolation trick to linear (#1564) 2022-05-13 10:52:39 +02:00
Edresson Casanova c6008e5235
Add audio length sampler balancer (#1561) 
* Add audio length sampler balancer

* Add unit tests
 2022-05-12 19:59:19 +02:00
Eren Gölge 6e460b7e42
Add an assert for the upsampling trick (#1538) 2022-05-12 19:55:24 +02:00
Eren Gölge e45ae57aef
Merge pull request #1550 from coqui-ai/fix-upsampling-asserts 
Fix VITS upsampling asserts
 2022-05-12 14:51:41 +02:00
Edresson Casanova 175ca06388 Add reinit text encoder and duration predictor parameter (#1562) 
* Add reinit encoder and duration predictor option

* Add .data to prevent any overlooked autograd hook
 2022-05-12 09:08:36 -03:00
Edresson Casanova 182711043c Fix the VITS upsampling asserts 
Fix style
 2022-05-12 09:08:29 -03:00
Eren Gölge c18bd21b3f Return durations at VITS inference 2022-05-11 11:30:05 +02:00
Eren Gölge 5021a03de0 Use torch.no_grad for VITS inference 2022-05-11 11:29:36 +02:00
Eren Gölge 3f03e3012c Fix batch_group_size in VITS 2022-05-07 13:44:44 +02:00
WeberJulian fbdf76b2fc returns y_mask in VITS inference (#1540) 
* returns y_mask

* make style
 2022-05-03 13:49:24 +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
Edresson Casanova 060e0f9368
Add EmbeddingManager and BaseIDManager (#1374) 2022-03-31 13:41:16 +02:00
Edresson Casanova 37896e1743
Bug fix in freeze encoder (#1391) 
* Fix the bug in freeze encoder

* Remove emb_l definition for non-multilingual training

* Fix unit tests
 2022-03-24 18:16:04 +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
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
Eren Gölge dd4287de1f Update models 2022-03-03 20:23:00 +01:00
Eren Gölge 1425a023fe Make style and lint 2022-03-02 13:25:35 +01:00
Eren Gölge c68885b3fd Update Vits speaker encoder init 2022-03-02 13:20:23 +01:00
Eren Gölge 27b67b7945 Fix import 2022-03-02 09:15:20 +01:00
Eren Gölge 942df0fb05 Update vits dataset 2022-03-02 09:14:32 +01:00
Eren Gölge 1e414b3a09 Make stlye 2022-02-25 11:31:56 +01:00
Eren Gölge acc83cd3e6 Update Vits model API 2022-02-25 11:31:56 +01:00
Eren Gölge fe656659be Implement BaseTTS 2022-02-25 11:31:56 +01:00
Eren Gölge 83c5ddc5b7 Update imports 2022-02-25 11:31:56 +01:00
Eren Gölge 14c117978d Fix return outputs 2022-02-25 11:31:56 +01:00
Eren Gölge 424d04e4f6 Make stlye 2022-02-25 11:31:56 +01:00
Eren Gölge c68962c574 Update forward tts binary loss 2022-02-25 11:30:24 +01:00
Eren Gölge 00c7600103 Update Vits model API 2022-02-25 11:30:24 +01:00
Eren Gölge 35fc7270ff Implement BaseTTS 2022-02-25 11:28:47 +01:00
Eren Gölge 1e219fef0a Revert drop_last 2022-02-25 11:26:59 +01:00
Eren Gölge 4b96bfe925 Fix train logging 2022-02-25 11:26:59 +01:00
Eren Gölge ab8a4ca2c3 Revert random segment 2022-02-25 11:26:59 +01:00
Eren Gölge 8622226f3f Make style 2022-02-25 11:26:59 +01:00
Eren Gölge 54c6bb2a8c Fix add speaker VITS 2022-02-25 11:26:59 +01:00
Eren Gölge 38314194e7 Set `drop_last` 2022-02-25 11:26:59 +01:00
Eren Gölge f70e4bb8c6 Add new speakers to the vits model 2022-02-25 11:26:59 +01:00
Eren Gölge 1f0c8179da Make style 2022-02-25 11:26:59 +01:00
Eren Gölge 34c4be5e49 Update forwardtts 2022-02-25 11:26:59 +01:00
Eren Gölge 2829027d8b Refactor VITS model 2022-02-25 11:26:59 +01:00
Eren Gölge ef63c99524 Implement `start_by_longest` option for TTSDatase 2022-02-25 11:26:18 +01:00
Eren Gölge 146fbfd7c9 Extend unittests 2022-02-25 11:25:00 +01:00
Eren Gölge 2fe16de8e3 Make lint 2022-02-25 11:25:00 +01:00
Eren Gölge 235f7d9b02 Extend glow_tts model tests 2022-02-25 11:24:13 +01:00
Eren Gölge 001da8afc8 Update Vits for the new model API 2022-02-25 11:21:19 +01:00
Eren Gölge 5176ae9e53 Fixes small compat. issues 2022-02-25 11:21:19 +01:00
Eren Gölge 4c5cb44eeb Update setup_model 2022-02-25 11:11:35 +01:00
Eren Gölge 7c4243fba7 Update GlowTTS 2022-02-25 11:11:35 +01:00
Eren Gölge bacf79f4fb Update AlignTTS 2022-02-25 11:11:35 +01:00
Eren Gölge 18f726af65 Update ForwardTTS 2022-02-25 11:11:35 +01:00
Eren Gölge d0ec4b91e5 Update Tacotron models 2022-02-25 11:11:35 +01:00
Eren Gölge ea965a5683 Update VITS for the new API 2022-02-25 11:11:35 +01:00
Eren Gölge 93957d58a1 Refactorin VITS for the tokenizer API 2022-02-25 11:05:06 +01:00
Eren Gölge 452dbc43d8 Update imports for symbols -> characters 2022-02-25 11:05:06 +01:00
Eren Gölge 8071fa0020 Refactor GlowTTS model and recipe for TTSTokenizer 2022-02-25 11:05:06 +01:00
Eren Gölge 7575367b9f Refactorin VITS for the tokenizer API 2022-02-25 10:57:35 +01:00
Eren Gölge 4cd690e4c1 Updates BaseTTS and configs 2022-02-25 10:57:35 +01:00
Eren Gölge 4597d4e5b6 Remove get_characters from BaseTTS 2022-02-25 10:48:03 +01:00
Eren Gölge 2d8ce98d2a Update imports for symbols -> characters 2022-02-25 10:48:03 +01:00
Eren Gölge 9a95e15483 Refactor GlowTTS model and recipe for TTSTokenizer 2022-02-25 10:48:03 +01:00
Eren Gölge 04202da1ac Make style 2022-02-25 10:48:03 +01:00
Eren Gölge bb389479a4 Update setup_model for TTS.tts models 2022-02-25 10:48:03 +01:00
Eren Gölge d2525abe8c Remove get_characters from BaseTTS 2022-02-25 10:48:03 +01:00
Eren Gölge 73d27ebd45 Fix GlowTTS 2022-02-25 10:48:03 +01:00
Eren Gölge fbad17e084 Update imports for symbols -> characters 2022-02-25 10:48:02 +01:00
Eren Gölge bd461ace33 Refactor GlowTTS model and recipe for TTSTokenizer 2022-02-25 10:45:24 +01:00
Edresson Casanova ba6e56e01c Fix Glow-TTS multi-speaker inference 2022-02-18 19:25:29 +00:00
Eren Gölge 127118c637
Update TTS.tts formatters (#1228) 
* Return Dict from tts formatters

* Make style
 2022-02-11 23:03:43 +01:00
WeberJulian e778bad626 Add argument to enable dp speaker conditioning 2022-01-06 15:07:27 +01:00
WeberJulian e1accb6e28
Fix train_tts.py and uncomment code (#1051) 
* Fix SE loading and language embedding logic

* remove trailing white space

* Uncomment resmapling code for SCL
 2022-01-03 17:44:57 +01:00
Eren Gölge 36cef5966b Fix resnet speaker encoder 2021-12-30 15:36:35 +00:00
Eren Gölge 348b5c96a2 Fix speaker encoder test 2021-12-30 15:36:35 +00:00
Eren Gölge 7129b04d46 Update VITS model 2021-12-30 14:08:17 +00:00
Eren Gölge d29c3780d1 Use speaker_encoder from speaker manager in Vits 2021-12-20 11:54:10 +00:00
Eren Gölge 649dc9e9da Remove redundant code 2021-12-20 11:54:10 +00:00
Eren Gölge 704dddcffa Make style 2021-12-20 11:54:10 +00:00
WeberJulian 2bbcb558dc Prevent weighted sampler use when num_gpus > 1 2021-12-20 11:54:10 +00:00
WeberJulian 74cedfac38 Revert init multispeaker change 2021-12-20 11:54:10 +00:00
WeberJulian 6b03943526 Move multilingual logic out of the trainer 2021-12-20 11:54:10 +00:00
Edresson 67dda0abe1 Add the SCL resample TODO 2021-12-20 11:54:10 +00:00
WeberJulian 8b52fb89d1 Fix merge bug 2021-12-20 11:54:10 +00:00
WeberJulian 09eda31a3f Fix tests 2021-12-20 11:54:10 +00:00
Edresson 78a23e19df Fix pylint checks 2021-12-20 11:54:10 +00:00
WeberJulian 4cd0e4eb0d Remove self.audio_config from VITS 2021-12-20 11:54:10 +00:00
Edresson d39200e69b Remove torchaudio requeriment 2021-12-20 11:54:10 +00:00
WeberJulian 2e516869a1 Fix trailing whitespace 2021-12-20 11:54:10 +00:00
WeberJulian ffc269eaf4 Update docstring 2021-12-20 11:54:10 +00:00
Edresson 12968532fe Add the language embedding dim in the duration predictor class 2021-12-20 11:54:10 +00:00
Edresson f34596d957 Fix function name 2021-12-20 11:54:10 +00:00
Edresson 9daa33d1fd Remove unusable speaker manager function 2021-12-20 11:54:10 +00:00
Edresson 6fc3b9e679 Remove the unusable fine-tuning model 2021-12-20 11:54:10 +00:00