… (to synthesize text from a text file)

… stop in the phonetic input and sentences are NOT delimited by [!]

…a single input text

v0.7.0

* Add Thorsten VITS model (coqui-ai#1675)

Co-authored-by: Eren Gölge <[email protected]>

* Remove GL message

Co-authored-by: WeberJulian <[email protected]>

…main

proposed by manmay-nakhashi in coqui-ai#1641

* Fix checkpointing GAN models (coqui-ai#1641)

* checkpoint sae step crash fix

* checkpoint save step crash fix

* Update gan.py

updated requested changes

* crash fix

* Fix the --model_name and --vocoder_name arguments need a <model_type> element (coqui-ai#1469)

Co-authored-by: Eren Gölge <[email protected]>

* Fix Publish CI (coqui-ai#1597)

* Try out manylinux

* temporary removal of useless pipeline

* remove check and use only manylinux

* Try --plat-name

* Add install requirements

* Add back other actions

* Add PR trigger

* Remove conditions

* Fix sythax

* Roll back some changes

* Add other python versions

* Add test pypi upload

* Add username

* Add back __token__ as username

* Modify name of entry to testpypi

* Set it to release only

* Fix version checking

* Fix tokenizer for punc only (coqui-ai#1717)

* Remove redundant config field

* Fix SSIM loss

* Separate loss tests

* Fix BCELoss adressing  coqui-ai#1192

* Make style

* Add durations as aux input for VITS (coqui-ai#1694)

* Add durations as aux input for VITS

* Make style

* Fix tts_tests

* Fix test_get_aux_input

* Make lint

* feat: updated recipes and lr fix (coqui-ai#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

* Implement VitsAudioConfig (coqui-ai#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

* Fix device allocation

* Fix SSIM loss correction

* Fix aux tests (coqui-ai#1753)

* Set n_jobs to 1 for resample script

* Delete resample test

* Set n_jobs 1 in vad test

* delete vad test

* Revert "Delete resample test"

This reverts commit bb7c846.

* Remove tests with resample

* Fix for FloorDiv Function Warning (coqui-ai#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

* Fix type in download_vctk.sh (coqui-ai#1739)

typo in comment

* Update decoder.py (coqui-ai#1792)

Minor comment correction.

* Update requirements.txt (coqui-ai#1791)

Support for coqui-ai#1775

* Update README.md (coqui-ai#1776)

Fix typo in different and code sample

* Fix & update WaveRNN vocoder model (coqui-ai#1749)

* Fixes KeyError bug. Adding logging to dashboard.

* Make pep8 compliant

* Make style compliant

* Still fixing style

* Fix rand_segment edge case (input_len == seg_len - 1)

* Update requirements.txt; inflect==5.6 (coqui-ai#1809)

New inflect version (6.0) depends on pydantic which has some issues irrelevant to 🐸 TTS. coqui-ai#1808 
Force inflect==5.6 (pydantic free) install to solve dependency issue.

* Update README.md; download progress bar in CLI. (coqui-ai#1797)

* Update README.md

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

* "added tqdm bar for model download"

* Update manage.py

* fixed style

* fixed style

* sort imports

* Update wavenet.py (coqui-ai#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"

* Adjust default to be able to process longer sentences (coqui-ai#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] mozilla/TTS#734

* Fix language flags generated by espeak-ng phonemizer (coqui-ai#1801)

* fix language flags generated by espeak-ng phonemizer

* Style

* Updated language flag regex to consider all language codes alike

* fix get_random_embeddings --> get_random_embedding (coqui-ai#1726)

* fix get_random_embeddings --> get_random_embedding

function typo leads to training crash, no such function

* fix typo

get_random_embedding

* Introduce numpy and torch transforms (coqui-ai#1705)

* Refactor audio processing functions

* Add tests for numpy transforms

* Fix imports

* Fix imports2

* Implement bucketed weighted sampling for VITS (coqui-ai#1871)

* Update capacitron_layers.py (coqui-ai#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)

* updates to dataset analysis notebooks for compatibility with latest version of TTS (coqui-ai#1853)

* Fix BCE loss issue (coqui-ai#1872)

* Fix BCE loss issue

* Remove import

* Remove deprecated files (coqui-ai#1873)

- samplers.py is moved
- distribute.py is replaces by the 👟Trainer

* Handle when no batch sampler (coqui-ai#1882)

* Fix tune wavegrad (coqui-ai#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

* Bump up to v0.8.0

* Add new DE Thorsten models (coqui-ai#1898)

- Tacotron2-DDC
- HifiGAN vocoder

Co-authored-by: manmay nakhashi <[email protected]>
Co-authored-by: camillem <[email protected]>
Co-authored-by: WeberJulian <[email protected]>
Co-authored-by: a-froghyar <[email protected]>
Co-authored-by: ivan provalov <[email protected]>
Co-authored-by: Tsai Meng-Ting <[email protected]>
Co-authored-by: p0p4k <[email protected]>
Co-authored-by: Yuri Pourre <[email protected]>
Co-authored-by: vanIvan <[email protected]>
Co-authored-by: Lars Kiesow <[email protected]>
Co-authored-by: rbaraglia <[email protected]>
Co-authored-by: jchai.me <[email protected]>
Co-authored-by: Stanislav Kachnov <[email protected]>

… (root_path is a part of items)

…nguage item

Add comments

…le in VITS

Add aux_input to propagate user parameters to inference

…` during training

🐬 v0.13.0

✨ v0.13.1

🌈 v0.13.2

🐶 v0.13.3

🐦 v0.14.0

Remove length_scale from default aux_input

… instead of flac

…idation

…nly when not defined at the sample/utterance level

Speaker name is prepended by dataset name in case of multispeaker datasets
Refactor "artic" formatter

Print speaker name notification

Merge changes by JMa into dev