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
4,517 Commits 80 Branches 98 Tags 314 MiB
Commit Graph

1871 Commits

Author SHA1 Message Date
Eren Gölge 9e5a469c64
d-vector handling (#1945) 
* Update BaseDatasetConfig

- Add dataset_name
- Chane name to formatter_name

* Update compute_embedding

- Allow entering dataset by args
- Use released model by default
- Use the new key format

* Update loading

* Update recipes

* Update other dep code

* Update tests

* Fixup

* Load multiple embedding files

* Fix argument names in dep code

* Update docs

* Fix argument name

* Fix linter
 2022-09-13 14:10:33 +02:00
Edresson Casanova 371772c355
Replace pyworld by pyin (#1946) 
* Replace pyworld by pyin

* Fix unit tests
 2022-09-09 10:43:14 +02:00
happylittlecat 4546b4cbd8
Add espeak support for Chinese (#1905) 
* fix description

* add espeak support for chinese

* add espeak support for chinese
 2022-09-08 12:32:41 +02:00
harmlessman 5abbe56642
Korean Phonemizer (#1822) 
* Update requirements.txt

install jamo for korean

* Update formatters.py

add KSS formatter

KSS is a korean single speech dataset (12hours)

* Add files via upload

add phonemizer for korean

* Add files via upload

add korean phonemizer

* Update requirements.txt

* change code style with `black` and `pylint`

* reflecting pylint's Evaluation

* reflecting pylint's Evaluation

* reflecting pylint's Evaluation-2

* isort

* edit about separator
write test case and add 'nltk' for requirements.txt

* add korean g2p (g2pkk)

* isort

* TTS/tts/utils/text/phonemizers/ko_kr_phonemizer.py:43:24: W0621: Redefining name 'text' from outer scope (line 58) (redefined-outer-name)

TTS/tts/utils/text/korean/korean.py:28:8: R1705: Unnecessary "else" after "return" (no-else-return)

* black
 2022-09-08 12:06:07 +02:00
Edresson Casanova 159eeeef64
Fix find unique phonemes script (#1928) 
* Fix find unique phonemes script

* Fix unit tests
 2022-09-08 10:17:35 +02:00
KyuubiYoru 3b7dff568a
Fixes a race condition with multiple simultaneous get requests. (#1807) 
* Fixes a race condition with multiple simultaneous get requests.

* Removed unused import

* Removed unused threading import

* Changed lock style to notation

* make style

Co-authored-by: WeberJulian <julian.weber@hotmail.fr>
 2022-09-08 10:16:16 +02:00
Julian Weber bb59718c03
Add capacitron v2 model (#1768) 
* Add capacitron v2 in .models.json

* Put right commit hash
 2022-09-08 09:43:56 +02:00
Edresson Casanova 096b35f639
Add VCTK speaker encoder recipe (#1912) 2022-08-26 16:19:03 +02:00
Eren Gölge e5430a6519
Add new DE Thorsten models (#1898) 
- Tacotron2-DDC
- HifiGAN vocoder
 2022-08-22 11:27:39 +02:00
Eren G??lge 8845f06fd9 Bump up to v0.8.0 2022-08-22 11:26:47 +02:00
Stanislav Kachnov 2c9f00a808
Fix tune wavegrad (#1844) 
* fix imports in tune_wavegrad

* load_config returns Coqpit object instead None

* set action (store true) for flag "--use_cuda"; start to tune if module is running as the main program

* fix var order in the result of batch collating

* make style

* make style with black and isort
 2022-08-22 09:55:32 +02:00
Eren Gölge fcb0bb58ae
Handle when no batch sampler (#1882) 2022-08-18 11:26:04 +02:00
Eren Gölge 7442bcefa5
Remove deprecated files (#1873) 
- samplers.py is moved
- distribute.py is replaces by the 👟Trainer
 2022-08-15 12:16:37 +02:00
Eren Gölge 4333492341
Fix BCE loss issue (#1872) 
* Fix BCE loss issue

* Remove import
 2022-08-15 11:27:21 +02:00
manmay nakhashi e4db7c51b5
Update capacitron_layers.py (#1664) 
crashing because of dimension miss match   at line no. 57
[batch, 256] vs [batch , 1, 512]
enc_out = torch.cat([enc_out, speaker_embedding], dim=-1)
 2022-08-15 11:08:50 +02:00
Eren Gölge bfc63829ac
Implement bucketed weighted sampling for VITS (#1871) 2022-08-15 11:08:11 +02:00
Eren Gölge d46fbc240c
Introduce numpy and torch transforms (#1705) 
* Refactor audio processing functions

* Add tests for numpy transforms

* Fix imports

* Fix imports2
 2022-08-08 11:57:50 +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
rbaraglia 75ac9e3f0c
Fix language flags generated by espeak-ng phonemizer (#1801) 
* fix language flags generated by espeak-ng phonemizer

* Style

* Updated language flag regex to consider all language codes alike
 2022-08-07 13:57:40 +02:00
Lars Kiesow 8c645080ac
Adjust default to be able to process longer sentences (#1835) 
Running `tts --text "$text" --out_path …` with a somewhat longer
sentences in the text will lead to warnings like “Decoder stopped with
max_decoder_steps 500” and the sentences just being cut off in the
resulting WAV file.

This happens quite frequently when feeding longer texts (e.g. a blog
post) to `tts`. It's particular frustrating since the error is not
always obvious in the output. You have to notice that there are missing
parts. This is something other users seem to have run into as well [1].

This patch simply increases the maximum number of steps allowed for the
tacotron decoder to fix this issue, resulting in a smoother default
behavior.

[1] https://github.com/mozilla/TTS/issues/734
 2022-08-07 13:51:29 +02:00
p0p4k 903a77c197
Update wavenet.py (#1796) 
* Update wavenet.py

Current version does not use "in_channels" argument. 
In glowTTS, we use normalizing flows and so "input dim" == "ouput dim" (channels and length). So, the existing code just uses hidden_channel sized tensor as input to first layer as well as outputs hidden_channel sized tensor. 
However, since it is a generic implementation, I believe it is better to update it for a more general use.

* "in_channels -> hidden_channels"
 2022-08-01 12:20:37 +02:00
p0p4k 4fe50801b5
Update README.md; download progress bar in CLI. (#1797) 
* Update README.md

- minor PR
- added model_info usage guide based on #1623 in README.md .

* "added tqdm bar for model download"

* Update manage.py

* fixed style

* fixed style

* sort imports
 2022-08-01 12:17:47 +02:00
Eren G??lge 7d8b1665c8 Fix rand_segment edge case (input_len == seg_len - 1) 2022-08-01 11:37:45 +02:00
vanIvan 5094499eba
Fix & update WaveRNN vocoder model (#1749) 
* Fixes KeyError bug. Adding logging to dashboard.

* Make pep8 compliant

* Make style compliant

* Still fixing style
 2022-07-26 15:05:11 +02:00
p0p4k 10195c4eba
Update decoder.py (#1792) 
Minor comment correction.
 2022-07-26 13:06:06 +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 f7587fc134
Fix SSIM loss correction 2022-07-13 10:47:12 +02:00
Eren Gölge bc1f93c299
Fix device allocation 2022-07-12 19:05:25 +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
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 48a4f3647f Make lint 2022-07-12 14:58:26 +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 G??lge 2cf89b88c9 Make style 2022-07-12 14:12:57 +02:00
Eren G??lge a6f73a18cb Fix BCELoss adressing #1192 2022-07-12 14:11:34 +02:00
Eren G??lge c17ff17a18 Fix SSIM loss 2022-07-12 12:35:24 +02:00
Eren G??lge f1e35596e8 Remove redundant config field 2022-07-11 13:39:41 +02:00
WeberJulian 5cef6facb0
Fix tokenizer for punc only (#1717) 2022-07-06 22:59:41 +02:00
camillem 5c821d9fa1
Fix the --model_name and --vocoder_name arguments need a <model_type> element (#1469) 
Co-authored-by: Eren Gölge <erogol@hotmail.com>
 2022-06-27 10:32:43 +02:00
manmay nakhashi 577ec406f4
Fix checkpointing GAN models (#1641) 
* checkpoint sae step crash fix

* checkpoint save step crash fix

* Update gan.py

updated requested changes

* crash fix
 2022-06-22 12:07:46 +02:00
Eren G??lge 00e67092d8 Bump up to v0.7.1 2022-06-21 14:12:55 +02:00
Eren G??lge 3328be7a8e Remove GL message 2022-06-21 12:39:31 +02:00
WeberJulian 30c72e0d05
Add Thorsten VITS model (#1675) 
Co-authored-by: Eren Gölge <egolge@coqui.ai>
 2022-06-21 11:39:49 +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
Eren G??lge 8b75e8be9c Bump up to v0.7.0 2022-06-20 13:50:09 +02:00
WeberJulian 6126c23498
Add synpaflex formatter (#1616) 
* Add synpaflex formatter

* Fix formatter

* Make style
 2022-06-20 13:36:26 +02:00
WeberJulian f09ea11c71
Internal formatter (#1629) 
* Add coqui formatter

* Make style
 2022-06-08 14:31:03 +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
Noran Raskin a790df4e94
Training recipes for thorsten dataset (#1020) 
* Fix style

* Fix isort

* Remove tensorboardX from requirements

Co-authored-by: logan hart <72301874+loganhart420@users.noreply.github.com>
Co-authored-by: Eren Gölge <egolge@coqui.ai>
 2022-05-30 12:07:31 +02:00
André R. de Miranda 3b84ef9524
Fixed use_cuda issue in compute_embeddings.py 
Added use_cuda argument in self.init_encoder method
 2022-05-20 12:46:46 -03:00
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 4857967063
🐍 Python 3.10.x support and drop Python 3.6 support (#1565) 
* Update requirements

* Update CI for p3.10

* Update numpy requirement

* Drop 🐍p3.6 support

Numpy also dropped support for p3.6

* Bind cython v0.29.28

* Bind pyworld to v0.2.10

> 0.2.10 is not p3.10.x compatible

* Update Dockerfile
 2022-05-12 15:50:25 +02:00
Edresson Casanova a97eed696a
Fix the bug in eSpeak wrapper for eSpeak version 1.48.15 (#1560) 2022-05-12 15:15:18 +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 2fc38f67d2 Update SpeakerManager init in Synthesizer 2022-05-11 11:32:27 +02:00
Eren Gölge c3f8c4d5eb Return default SpeakerManager if no d_vector_file 2022-05-11 11:31:45 +02:00
Eren Gölge 121e9ed685 Pass use_cuda to init_encoder 2022-05-11 11:31:17 +02:00
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
code-review-doctor fa887ef5f9
Fix issue probably-meant-fstring found at https://codereview.doctor (#1532) 2022-05-07 13:33:40 +02:00
Eren Gölge a0a9279e4b Fix GAN optimizer order 
commit 212d330929
Author: Edresson Casanova <edresson1@gmail.com>
Date:   Fri Apr 29 16:29:44 2022 -0300

    Fix unit test

commit 44456b0483
Author: Edresson Casanova <edresson1@gmail.com>
Date:   Fri Apr 29 07:28:39 2022 -0300

    Fix style

commit d545beadb9
Author: Edresson Casanova <edresson1@gmail.com>
Date:   Thu Apr 28 17:08:04 2022 -0300

    Change order of HIFI-GAN optimizers to be equal than the original repository

commit 657c5442e5
Author: Edresson Casanova <edresson1@gmail.com>
Date:   Thu Apr 28 15:40:16 2022 -0300

    Remove audio padding before mel spec extraction

commit 76b274e690
Merge: 379ccd7b 6233f4fc
Author: Edresson Casanova <edresson1@gmail.com>
Date:   Wed Apr 27 07:28:48 2022 -0300

    Merge pull request #1541 from coqui-ai/comp_emb_fix

    Bug fix in compute embedding without eval partition

commit 379ccd7ba6
Author: WeberJulian <julian.weber@hotmail.fr>
Date:   Wed Apr 27 10:42:26 2022 +0200

    returns y_mask in VITS inference (#1540)

    * returns y_mask

    * make style
 2022-05-07 13:29:11 +02:00
Edresson Casanova 60034674f9 Remove audio padding before mel spec extraction 2022-05-07 13:12:09 +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 6233f4fcd7 Bug fix in compute embedding without eval partition 2022-04-26 13:58:03 -03:00
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
Eren Gölge c410bc58ef Bump to v0.6.2 2022-04-20 11:46:26 +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
WeberJulian 4953636b14
Add African models (#1511) 
* Add african models

* Set default license for all models
 2022-04-19 14:18:30 +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 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
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 3af01cfe3b
Update base model wrt 👟 (#1406) 2022-03-23 17:24:20 +01:00
Eren Gölge 1c3623af33
Fix model manager (#1436) 
* Fix manager

* Make style
 2022-03-23 12:57:14 +01:00
Eren Gölge 72d85e53c9
Update model file extension (#1422) 
* Update model file ext to ```.pth```

* Update docs

* Rename more

* Find model files
 2022-03-22 17:55:00 +01:00
Eren Gölge fd56fabb21
Fix #1380 (#1409) 2022-03-16 12:38:27 +01:00
Eren Gölge 0870a4faa2
Make style (#1405) 2022-03-16 12:13:55 +01:00
WeberJulian 690c96ed28
Fix default phonemizer for ja and zh (#1399) 2022-03-16 12:13:22 +01:00
Edresson Casanova f81892483d
REBASED: Transform Speaker Encoder in a Generic Encoder and Implement Emotion Encoder training support (#1349) 
* Rename Speaker encoder module to encoder

* Add a generic emotion dataset formatter

* Transform the Speaker Encoder dataset to a generic dataset and create emotion encoder config

* Add class map in emotion config

* Add Base encoder config

* Add evaluation encoder script

* Fix the bug in plot_embeddings

* Enable Weight decay for encoder training

* Add argumnet to disable storage

* Add Perfect Sampler and remove storage

* Add evaluation during encoder training

* Fix lint checks

* Remove useless config parameter

* Active evaluation in speaker encoder test and use multispeaker dataset for this test

* Unit tests fixs

* Remove useless tests for speedup the aux_tests

* Use get_optimizer in Encoder

* Add BaseEncoder Class

* Fix the unitests

* Add Perfect Batch Sampler unit test

* Add compute encoder accuracy in a function
 2022-03-11 14:43:40 +01:00
Edresson Casanova 36e9ea2f97
Open bible dataset formatter (#1365) 
* Add support for voice conversion inference

* Cache d_vectors_by_speaker for fast inference using a bigger speakers.json

* Rebase bug fix

* Use the average d-vector for inference

* Fix the bug in find unique chars script

* Add OpenBible formatter

Co-authored-by: Eren Gölge <erogol@hotmail.com>
 2022-03-11 10:43:31 +01:00
Edresson Casanova dbe9da7f15
Add Voice conversion inference support (#1337) 
* Add support for voice conversion inference

* Cache d_vectors_by_speaker for fast inference using a bigger speakers.json

* Rebase bug fix

* Use the average d-vector for inference
 2022-03-10 14:57:12 +01:00
Edresson Casanova 917f417ac4
Add alphas to control language and speaker balancer (#1216) 
* Add alphas to control language and speaker balancer

* Add docs for speaker and language samplers

* Change the Samplers weights to float for save memory

* Change the test_samplers to unittest format

* Add get_sampler method in BaseTTS

* Fix rebase issues

* Add language and speaker samplers support for DDP training

* Rename distributed sampler wrapper

* Remove the DistributedSamplerWrapper and use the one from Trainer

* Bugfix after rebase

* Move the samplers config to tts config
 2022-03-10 14:56:09 +01:00
Edresson Casanova f381e29b91
REBASED: Add support for the speaker encoder training using torch spectrograms (#1348) 
* Add support for the speaker encoder training using torch spectrograms

* Remove useless function in speaker encoder dataset class
 2022-03-10 14:54:51 +01:00
Eren Gölge c670365507 Fix VCTK recipe and formatter 2022-03-08 14:20:34 +01:00
Eren Gölge 8feb41d361 Bump up to v0.6.1 2022-03-07 15:57:44 +01:00
Eren Gölge ee02bc3823 Bump up to v0.6.0 2022-03-07 12:08:22 +01:00
Eren Gölge dc280819be Add new models 2022-03-07 12:08:09 +01:00
Eren Gölge e9d9028b4d Revert cleaner name 2022-03-06 12:57:06 +01:00
Eren Gölge 764c7fa4a4 Rename phoneme_cleaners 2022-03-06 12:09:54 +01:00
Eren Gölge dd4287de1f Update models 2022-03-03 20:23:00 +01:00
Eren Gölge 6cb00be795 Update your_tts model URL 2022-03-02 18:04:49 +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 6a9f8074f0 Fix TTSDataset 2022-03-01 07:57:48 +01:00
Eren Gölge 690de1ab06 Update Characters and add more tests 2022-02-25 11:32:44 +01:00
Eren Gölge 9063397892 Fix FastSpeech config 2022-02-25 11:31:56 +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 bed4afd4ee Implement BaseVocabulary 2022-02-25 11:31:56 +01:00
Eren Gölge e0f9be76c0 Update test_run in wavernn and wavegrad 2022-02-25 11:31:56 +01:00
Eren Gölge bf540f4323 Update imports for trainer 2022-02-25 11:31:56 +01:00
Eren Gölge 4c43eda414 Update BaseTrainerModel 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 8b3ba02c95 Add vocab_dict to model config 2022-02-25 11:31:20 +01:00
Eren Gölge ff23dce081 Update TTSDataset 2022-02-25 11:31:20 +01:00
Eren Gölge 750903d2ba Add VCTK formatter docstring 2022-02-25 11:30:24 +01:00
Eren Gölge 52a7896668 Update VITS loss 2022-02-25 11:30:24 +01:00
Eren Gölge c68962c574 Update forward tts binary loss 2022-02-25 11:30:24 +01:00
Eren Gölge c11944022d Revert back again rand_segment 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 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 35fc7270ff Implement BaseTTS 2022-02-25 11:28:47 +01:00
Eren Gölge 2bad098625 Implement BaseVocabulary 2022-02-25 11:28:47 +01:00
Eren Gölge 833de62e30 Update base_vocoder 2022-02-25 11:28:14 +01:00
Eren Gölge fc3b6d2861 Update gan 2022-02-25 11:28:14 +01:00
Eren Gölge 20a677c623 Update test_run in wavernn and wavegrad 2022-02-25 11:28:14 +01:00
Eren Gölge be3a03126a Update imports for trainer 2022-02-25 11:28:14 +01:00
Eren Gölge c911729896 Update BaseTrainerModel 2022-02-25 11:28:14 +01:00
Eren Gölge 1e219fef0a Revert drop_last 2022-02-25 11:26:59 +01:00
Eren Gölge 7dfd753d91 Add a cheap trick to avoid short audio clips 2022-02-25 11:26:59 +01:00
Eren Gölge 1a43e05460 Fix VITS loss bug 
Fake and real features were given in the wrong args order to
the loss function
 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 27db089d6c Change TrainingArgs -> TrainerArgs 2022-02-25 11:26:59 +01:00
Eren Gölge aa81454721 Update BaseTrainingConfig 2022-02-25 11:26:59 +01:00
Eren Gölge d3a58ed07a Fix default values 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 590b04fb89 Fix espeak_wrapper 2022-02-25 11:26:59 +01:00
Eren Gölge a013566d15 Delete trainer related code 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 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 b3ed6ff6b7 Update FastPitchConfig 2022-02-25 11:26:59 +01:00
Eren Gölge 1932401e8d Fix dataset preprocessing 2022-02-25 11:26:59 +01:00
Eren Gölge 34c4be5e49 Update forwardtts 2022-02-25 11:26:59 +01:00
Eren Gölge bb37462794 Update language manager 2022-02-25 11:26:59 +01:00
Eren Gölge 5169d4eb32 Plot pitch over input characters 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 7058fcc3ff Take file extension as an argument 2022-02-25 11:26:59 +01:00
Eren Gölge 13482dde1f Update GAN model 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 c4c471d61d Allow padding for shorter segments 2022-02-25 11:25:48 +01:00
Eren Gölge 47fbddc8d4 Fix docstring 2022-02-25 11:25:48 +01:00
Eren Gölge bc2243bac4 Fix tests 2022-02-25 11:25:00 +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 7b49a4aa2b Fix glow_tts_config missing field 2022-02-25 11:24:13 +01:00
Eren Gölge 07b0a80d57 Fix tokenizer init_from_config 2022-02-25 11:24:13 +01:00
Eren Gölge 50e17097a7 Add verbose option to AudioProcessor 2022-02-25 11:24:13 +01:00
Eren Gölge 235f7d9b02 Extend glow_tts model tests 2022-02-25 11:24:13 +01:00
Eren Gölge 8e248913d6 Update train_tts for the new API 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 131bc0cfc0 Fix synthesis.py 🔧 2022-02-25 11:18:00 +01:00
Eren Gölge c0746f23df Fix `too many open files` 2022-02-25 11:16:30 +01:00
Eren Gölge df0d58bf09 Update VCTK recipes 2022-02-25 11:16:30 +01:00
Eren Gölge 730f7c0df4 Add file_ext args to resample.py 2022-02-25 11:15:46 +01:00
Eren Gölge 28d98da422 Update VCTK formatter 2022-02-25 11:15:46 +01:00
Eren Gölge 4d99fee3e2 Update spec extractor 2022-02-25 11:12:44 +01:00
Eren Gölge 38a0b3b6c7 Update train_tts.py 2022-02-25 11:11:35 +01:00
Eren Gölge cfaa51fddc Update BaseTTS config 2022-02-25 11:11:35 +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 f802a931a3 Pass samples to init_from_config in SpeakerManager 2022-02-25 11:07:34 +01:00
Eren Gölge bde68d9f25 Use the same phonemizer for `en` to `en-us` 2022-02-25 11:07:34 +01:00
Eren Gölge 8649d4fd36 Allow None pad and blank tokens 2022-02-25 11:07:34 +01:00
Eren Gölge c9972e6f14 Make lint 2022-02-25 11:07:34 +01:00
Eren Gölge 30cfafce56 Add init_from_config 2022-02-25 11:05:54 +01:00
Eren Gölge 90cc45dd4e Update data loader tests 2022-02-25 11:05:54 +01:00
Eren Gölge 93957d58a1 Refactorin VITS for the tokenizer API 2022-02-25 11:05:06 +01:00
Eren Gölge 04df0a3d9f Refactor TTSDataset ⚡️ 2022-02-25 11:05:06 +01:00
Eren Gölge 9bb347a52b Update for 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 b6c2bfdf08 Refactor synthesis.py for TTSTokenizer 2022-02-25 11:05:06 +01:00
Eren Gölge b2bb954a51 Refactor TTSDataset to use TTSTokenizer 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 196ae74273 Update data loader tests 2022-02-25 11:05:06 +01:00
Eren Gölge 98057a00ae Make style 2022-02-25 10:57:35 +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 176b712c1a Refactor TTSDataset ⚡️ 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 1df1d6c4a9 Update for tokenizer API 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 d0eb642d88 Refactor synthesis.py for TTSTokenizer 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 a71a013276 Fix the wrong default loss name for GAN models 2022-02-25 10:48:03 +01:00
Eren Gölge 04202da1ac Make style 2022-02-25 10:48:03 +01:00
Eren Gölge 3b63d713b9 Fix espeak wrapper cmd call 2022-02-25 10:48:03 +01:00
Eren Gölge 4894998e6b Fix print_logs 2022-02-25 10:48:03 +01:00
Eren Gölge 4e8f9d6f10 Fix IPAPhonemes init_from_config 2022-02-25 10:48:03 +01:00
Eren Gölge 0fe39166fe Discard OOV chars in tokenizer 
Discard but store OOV chars with a warninig message
when the OOV char first recognized
 2022-02-25 10:48:03 +01:00
Eren Gölge c39aaafbfc Update EspeakWrapper for espeak-ng 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 9b83e665fc Add init_from_config as an abstract class 2022-02-25 10:48:03 +01:00
Eren Gölge 3eca5ad060 Update config fields for phonemizer 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 87bf940676 Print duplicate characters 2022-02-25 10:48:03 +01:00
Eren Gölge 3de9f38d16 Add init_from_config to SpeakerManager 2022-02-25 10:48:03 +01:00
Eren Gölge d8ec7086b6 Update `synthesis` for the new API 2022-02-25 10:48:03 +01:00
Eren Gölge 4e83bf3968 Allow choosing phonemizer 2022-02-25 10:48:02 +01:00
Eren Gölge 22f0c58fe1 Print language codes 2022-02-25 10:48:02 +01:00
Eren Gölge 693fb4dd39 Modify init_from_config for IPAPhonemes 2022-02-25 10:48:02 +01:00
Eren Gölge acc6eef625 Update for tokenizer API 2022-02-25 10:48:02 +01:00
Eren Gölge e1b4c4ca43 Add init_from_config to GAN 2022-02-25 10:48:02 +01:00
Eren Gölge 353f913efc Fix #985 2022-02-25 10:48:02 +01:00
Eren Gölge ba3b60c90f Test TTSTokenizer 2022-02-25 10:48:02 +01:00
Eren Gölge 79a84410f2 Test punctuations 2022-02-25 10:48:02 +01:00
Eren Gölge d8bdeb8b8f Fix Punctuation 2022-02-25 10:48:02 +01:00
Eren Gölge ff7c385838 Fix BasePhonemizer 2022-02-25 10:48:02 +01:00
Eren Gölge 10d435ce77 Fixup 2022-02-25 10:48:02 +01:00
Eren Gölge f0655bfffc Fix ja_jp_phonemizer 2022-02-25 10:48:02 +01:00
Eren Gölge 20e5dd3678 Add doc examples 2022-02-25 10:48:02 +01:00
Eren Gölge fbad17e084 Update imports for symbols -> characters 2022-02-25 10:48:02 +01:00
Eren Gölge a1df4f9887 Test character classes 2022-02-25 10:45:24 +01:00
Eren Gölge bd461ace33 Refactor GlowTTS model and recipe for TTSTokenizer 2022-02-25 10:45:24 +01:00
Eren Gölge 5a9653978a Refactor synthesis.py for TTSTokenizer 2022-02-25 10:45:24 +01:00
Eren Gölge e5785b34b0 Style fix 2022-02-25 10:27:46 +01:00
Eren Gölge e4049aa31a Refactor TTSDataset to use TTSTokenizer 2022-02-25 10:27:46 +01:00
Eren Gölge 2480bbe937 Remove OLD TOKENIZATION ROUTINES 2022-02-25 09:32:54 +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 8d85af84cd Implement Punctuation class 2022-02-25 09:32:54 +01:00
Eren Gölge 1aca58afaf Fix imports in cleaners.py 2022-02-25 09:32:54 +01:00
Eren Gölge 0344645e90 Implement TTSTokenizer 2022-02-25 09:32:54 +01:00
Eren Gölge 2fb1f70503 Implement BaseCharacters, IPAPhonemes, Graphemes 2022-02-25 09:32:54 +01:00
Eren Gölge 1bee40af40 Create language folders under `TTS.tts.utils.text` 2022-02-25 09:32:54 +01:00
Eren Gölge c1119bc291 Implement BasePhonemizer 2022-02-25 09:32:54 +01:00
Eren Gölge dcd01356e0 Create `text/english` folder 2022-02-25 09:32:54 +01:00
Eren Gölge 80867c8e8c Implement multi-phonemizer 2022-02-25 09:32:54 +01:00
Eren Gölge 5e4f78add3 Implement espeak wrapper 2022-02-25 09:32:54 +01:00
Eren Gölge e03a05c816 Implement gruut wrapper 2022-02-25 09:32:54 +01:00
Eren Gölge 172ba0c5e7 Implement JA_JP phonemizer 2022-02-25 09:32:54 +01:00
Eren Gölge ca02b82218 Implement ZH_CH phonemizer 2022-02-25 09:32:54 +01:00
Eren Gölge a51b031bff
Merge branch 'dev' into dev-fix-glowtts-infer 2022-02-21 12:01:40 +03:00
Edresson Casanova 28a7464975
Fix the bug in split dataset function (#1251) 
* Fix the bug in split_dataset

* Make eval_split_size configurable

* Change test_loader to use load_tts_samples function

* Change eval_split_portion to eval_split_size and permits to set the absolute number of samples in eval

* Fix samplers unit test

* Add data unit test on GitHub workflow
 2022-02-21 11:59:36 +03:00
Edresson Casanova bc5db13d06 Fix the bug in extract tts spectrogram script 2022-02-19 19:24:00 +00:00
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
Eren Gölge 5e3f499a69
Fix #1187 (#1227) 2022-02-11 13:27:59 +01:00
Edresson Casanova 0860d73cf8
Remove Tensorflow requeriment (#1225) 
* Remove TF modules

* Remove TF unit tests

* Remove TF vocoder modules

* Remove TF convert scripts

* Remove TF requirement

* Remove the Docs TF instructions

* Remove TF inference support
 2022-02-10 16:14:54 +01:00
Eren Gölge 44c7d1a826
Merge pull request #1054 from WeberJulian/partial_embedding_compute 
Partial embedding compute
 2022-02-06 20:13:55 +01:00
WeberJulian c7f5e005e1 Compute embedding for new audios only 2022-01-06 15:41:38 +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 58c38de58d Bump up to v0.5.0 2022-01-03 15:04:03 +00:00
Eren Gölge 5840d89802 Keep proj_dim in speaker encoder models 2022-01-03 15:03:34 +00:00
Eren Gölge 03bcae1ba5
Merge pull request #1050 from coqui-ai/fix_synthesizer_init 
Fix if else statement
 2022-01-03 15:59:29 +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 d724984be1 Fix language assignment 2022-01-02 11:11:24 +00:00
WeberJulian a63998c048 Fix phoneme language 2022-01-01 21:08:13 +01:00
Eren Gölge 7ef458a59c Updake default vocoder for uk model 2022-01-01 16:09:42 +00:00
Eren Gölge e55f5ee59e Make linter 2022-01-01 15:50:04 +00:00
Eren Gölge 38f5a11125 Merge branch 'dev' of https://github.com/coqui-ai/TTS into dev 2022-01-01 15:38:46 +00:00
Eren Gölge c5512af82b Update uk vocoder url 2022-01-01 15:38:21 +00:00
Eren Gölge d37cfe474a Merge branch 'pr/Edresson/731-rebased' into dev 2022-01-01 15:37:35 +00:00
Eren Gölge 33711afa01 Update yourTTS url 2022-01-01 15:37:08 +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 8100135a7e Add the YourTTS entry to the models 2021-12-31 12:22:08 +00:00
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 638091f41d Update Speaker Encoder models 2021-12-30 12:02:06 +00:00
Eren Gölge 6189fdfaea Fix Training HiFiGan -- avg loss not decreasing #1003 2021-12-30 10:48:55 +00:00
Eren Gölge 275c759993 Fix #1037 2021-12-23 15:57:10 +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 8d2bb284ac Add UK vocoder models 2021-12-21 13:13:35 +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