What's Changed

fix: Few typos in Tortoise docs. by @VladCuciureanu in https://github.com/coqui-ai/TTS/pull/3352
fix pause problem of Chinese speech by @aaron-lii in https://github.com/coqui-ai/TTS/pull/3351
Fix typos by @omahs in https://github.com/coqui-ai/TTS/pull/3368
Print message for either commercial license or CPML by @JRMeyer in https://github.com/coqui-ai/TTS/pull/3381
Add inference parameters by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3373
Training fastspeech2 with External Speaker Embeddings by @freds0 in https://github.com/coqui-ai/TTS/pull/3404
fixes a typo by @joelhoward0 in https://github.com/coqui-ai/TTS/pull/3392
support multiple GPU training for XTTS by @aaron-lii in https://github.com/coqui-ai/TTS/pull/3391
Add studio speakers to open source XTTS! by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3405

New Contributors

@VladCuciureanu made their first contribution in https://github.com/coqui-ai/TTS/pull/3352
@aaron-lii made their first contribution in https://github.com/coqui-ai/TTS/pull/3351
@omahs made their first contribution in https://github.com/coqui-ai/TTS/pull/3368
@JRMeyer made their first contribution in https://github.com/coqui-ai/TTS/pull/3381
@freds0 made their first contribution in https://github.com/coqui-ai/TTS/pull/3404
@joelhoward0 made their first contribution in https://github.com/coqui-ai/TTS/pull/3392

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.21.3...v0.22.0

- Python
Published by erogol about 2 years ago

What's Changed

Add XTTS Fine tuning gradio demo by @Edresson in https://github.com/coqui-ai/TTS/pull/3296

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.21.2...v0.21.3

No-Code XTTS fine-tuning

We created a UI that you can use to fine-tune XTTS with your data. You can run it on Colab, locally, or on a server.

@WeberJulian has also recorded a video for showing step-by-step tutorial

You can also follow the XTTS docs if you are a read-and-learn type.

- Python
Published by erogol about 2 years ago

What's Changed

Run XTTS models by direct name with versions by @erogol in https://github.com/coqui-ai/TTS/pull/3318
fix: correctly strip/restore initial punctuation by @eginhard in https://github.com/coqui-ai/TTS/pull/3336
Fix link to installation instructions by @Vuizur in https://github.com/coqui-ai/TTS/pull/3329

New Contributors

@Vuizur made their first contribution in https://github.com/coqui-ai/TTS/pull/3329

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.21.1...v0.21.2

This PR allows for running XTTS models with version tags. So you the user can access any version they like.

```python from TTS.api import TTS

get v2.0.2

tts = TTS(modelname="xttsv2.0.2", gpu=True)

get the latest version

tts = TTS(model_name="xtts", gpu=True)

generate speech by cloning a voice using default settings

tts.ttstofile(text="Here is my sample text.", filepath="output.wav", speakerwav=["reference.wav", "reference1.wav"], language="en") ```

Making automatic sentence splitting optional. So you can apply any custom logic for processing the text before passing it to the model. Set split_sentences False.

```python from TTS.api import TTS

get v2.0.2

tts = TTS(modelname="xttsv2.0.2", gpu=True)

generate speech by cloning a voice using default settings

tts.ttstofile(text="Here is my sample text.", filepath="output.wav", speakerwav=["reference.wav", "reference1.wav"], language="en", split_sentences=False) ```

- Python
Published by erogol about 2 years ago

tts - v0.21.1

Adding a basic Hindi text cleaner. https://github.com/coqui-ai/TTS/commit/32065139e713b3e44aa88e72c4d35012bb888238

- Python
Published by erogol about 2 years ago

What's Changed

Remove duplicate/unused code by @eginhard in https://github.com/coqui-ai/TTS/pull/3243
Making the Model Manager's Progress bar statically accessible via the class. by @FlorianEagox in https://github.com/coqui-ai/TTS/pull/3297
More informative error for wrong --language argument by @eginhard in https://github.com/coqui-ai/TTS/pull/3294
Don't pass quotes to espeak by @eginhard in https://github.com/coqui-ai/TTS/pull/3286
Fix ttswithvc by @eginhard in https://github.com/coqui-ai/TTS/pull/3275
Misjudgment of is_multi_lingual When Loading Multilingual Model via model_path by @TITC in https://github.com/coqui-ai/TTS/pull/3273
Introducing Development Dockerfile by @Kaszanas in https://github.com/coqui-ai/TTS/pull/3263
update deepspeed version by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3281

New Contributors

@FlorianEagox made their first contribution in https://github.com/coqui-ai/TTS/pull/3297
@TITC made their first contribution in https://github.com/coqui-ai/TTS/pull/3273
@Kaszanas made their first contribution in https://github.com/coqui-ai/TTS/pull/3263

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.20.6...v0.21.0

- Python
Published by erogol about 2 years ago

What's Changed

Remove duplicate AudioProcessor code, fix ExtractTTSpectrogram.ipynb by @eginhard in https://github.com/coqui-ai/TTS/pull/3230
Add sentence splitting by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3227
Fix zh bug by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3238
Update versions by @erogol in https://github.com/coqui-ai/TTS/pull/3248
Ensures that only GPT model is in training mode during XTTS GPT training by @Edresson in https://github.com/coqui-ai/TTS/pull/3241
Loosen dependencies and make k_diffusion optional by @erogol in https://github.com/coqui-ai/TTS/pull/3249
Update XTTS v2.0.2 by @erogol in https://github.com/coqui-ai/TTS/pull/3249

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.20.5...v0.20.6

- Python
Published by erogol over 2 years ago

What's Changed

Add speed control for inference by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3214
Update README.md by @eltociear in https://github.com/coqui-ai/TTS/pull/3215
Fix XTTS GPT padding and inference issues by @Edresson in https://github.com/coqui-ai/TTS/pull/3216

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.20.4...v0.20.5

- Python
Published by erogol over 2 years ago

What's Changed

Update XTTS cloning by @erogol in https://github.com/coqui-ai/TTS/pull/3207
fix max generation length for XTTS by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3208

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.20.3...v0.20.4

- Python
Published by erogol over 2 years ago

What's Changed

XTTS- Torchaudio should use proper backend to load audio by @gorkemgoknar in https://github.com/coqui-ai/TTS/pull/3179
PyTorch 2.1 Updates (Weight Norm and TorchAudio I/O) by @MattyB95 in https://github.com/coqui-ai/TTS/pull/3176
xtts/tokenizer: merge duplicate implementations of preprocess_text by @akx in https://github.com/coqui-ai/TTS/pull/3170
fix(formatters): set missing root_path attribute by @eginhard in https://github.com/coqui-ai/TTS/pull/3182

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.20.2...v0.20.3

- Python
Published by erogol over 2 years ago

What's Changed

Add char limit warn by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3130
Fix coqui api by @erogol in https://github.com/coqui-ai/TTS/pull/3168
Fix #3153 by @erogol in https://github.com/coqui-ai/TTS/pull/3169
Move FreeVCConfig to TTS.vc.configs (like all other config classes) by @akx in https://github.com/coqui-ai/TTS/pull/3126
Fix ModelManager.list_models() by @eginhard in https://github.com/coqui-ai/TTS/pull/3128
Fix for exception on streaming on last chunk by @gorkemgoknar in https://github.com/coqui-ai/TTS/pull/3160
Add lang code in XTTS doc by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3158
Remove v1 doc and tests by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3172

New Contributors

@eginhard made their first contribution in https://github.com/coqui-ai/TTS/pull/3128
@gorkemgoknar made their first contribution in https://github.com/coqui-ai/TTS/pull/3160

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.20.1...v0.20.2

- Python
Published by erogol over 2 years ago

What's Changed

Drop diffusion from XTTS by @erogol in https://github.com/coqui-ai/TTS/pull/3150
Bug fixes and add support for multiples speaker references on XTTS inference by @Edresson in https://github.com/coqui-ai/TTS/pull/3149
Fix XTTS v2.0 training recipe by @Edresson in https://github.com/coqui-ai/TTS/pull/3154

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.20.0...v0.20.1

- Python
Published by erogol over 2 years ago

What's Changed

Run make style & re-enable it in CI by @akx in https://github.com/coqui-ai/TTS/pull/3127
XTTS v2.0 by @Edresson in https://github.com/coqui-ai/TTS/pull/3137

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.19.1...v0.20.0

- Python
Published by erogol over 2 years ago

What's Changed

Second round of issue fixing for XTTS v1.1 by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3103
fix for issue 3067 by @Aya-AlJafari in https://github.com/coqui-ai/TTS/pull/3109
Bug: self.model_name needed to be initialized. by @vltmedia in https://github.com/coqui-ai/TTS/pull/2983

New Contributors

@vltmedia made their first contribution in https://github.com/coqui-ai/TTS/pull/2983

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.19.0...v0.19.1

- Python
Published by erogol over 2 years ago

What's Changed

XTTS v1.1 GPT Trainer by @Edresson in https://github.com/coqui-ai/TTS/pull/3086

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.18.2...v0.19.0

- Python
Published by erogol over 2 years ago

What's Changed

Fix xtts v1.1 by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3096

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.18.1...v0.18.2

- Python
Published by erogol over 2 years ago

What's Changed

Bug fix on XTTS v1.1 inference by @Edresson and @WeberJulian in https://github.com/coqui-ai/TTS/pull/3093

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.18.0...v0.18.1

- Python
Published by Edresson over 2 years ago

What's Changed

XTTS v1.1 by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3089

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.17.10...v0.18.0

XTTS v1.1

This model is trained on top of XTTS v1, using output masking. We mask the part of the output that is used as the audio prompt while training and don't compute loss for that segment. This helps us to resolve the hallucination issue that V1 experienced.

Changes

Add Japanese
Resolve the hallucination issue (repeating the audio prompt)
Increased expressivity
Hash check to control model version
Added ne_hifigan that was trained without denoising that brought some EQ and compression profile that might be unwanted for some use-cases

- Python
Published by erogol over 2 years ago

tts - v0.17.10

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.17.9...v0.17.10

- Python
Published by erogol over 2 years ago

tts - v0.17.9

What's Changed

fixed bugs in fastpitch tts synthesis by @Aya-AlJafari in https://github.com/coqui-ai/TTS/pull/3058
Update AnalyzeDataset.ipynb by @meryemsakin in https://github.com/coqui-ai/TTS/pull/2783
Synthesizer skips over embeddings file if model only has one speaker by @wonkothesanest in https://github.com/coqui-ai/TTS/pull/2587
fixed typo of docs\source\implementinganew_model.md by @Subash-Lamichhane in https://github.com/coqui-ai/TTS/pull/3066
fixed typo of /docs by @Subash-Lamichhane in https://github.com/coqui-ai/TTS/pull/3065
Add play and speed to cli options by @David-bfg in https://github.com/coqui-ai/TTS/pull/3027
Fix doc dataset by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3070
fix readme by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3071

New Contributors

@meryemsakin made their first contribution in https://github.com/coqui-ai/TTS/pull/2783
@wonkothesanest made their first contribution in https://github.com/coqui-ai/TTS/pull/2587
@Subash-Lamichhane made their first contribution in https://github.com/coqui-ai/TTS/pull/3066
@David-bfg made their first contribution in https://github.com/coqui-ai/TTS/pull/3027

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.17.8...v0.17.9

- Python
Published by erogol over 2 years ago

tts - v0.17.8

What's Changed

XTTS redownload if needed by @Edresson in https://github.com/coqui-ai/TTS/pull/3038

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.17.7...v0.17.8

- Python
Published by gorkemgoknar over 2 years ago

tts - v0.17.7

What's Changed

Upgrade and Optimize TTS Code in extractttsspectrogram.ipynb by @anupammaurya6767 in https://github.com/coqui-ai/TTS/pull/3012
None is not able to be read for "XTTS", fixes crash if its set to None. by @OPPEYRADY in https://github.com/coqui-ai/TTS/pull/3009
Streaming inference for XTTS 🚀 by @WeberJulian in https://github.com/coqui-ai/TTS/pull/3035

New Contributors

@anupammaurya6767 made their first contribution in https://github.com/coqui-ai/TTS/pull/3012
@OPPEYRADY made their first contribution in https://github.com/coqui-ai/TTS/pull/3009

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.17.6...v0.17.7

- Python
Published by erogol over 2 years ago

tts - v0.17.6

What's Changed

Duplicate code removal by @akx in https://github.com/coqui-ai/TTS/pull/3003
Loosen dependency pins by @akx in https://github.com/coqui-ai/TTS/pull/3001
Remove unnecessary black exclude config by @akx in https://github.com/coqui-ai/TTS/pull/2999
Ensure tts CLI tool readme and usage is in sync by @akx in https://github.com/coqui-ai/TTS/pull/2993
Adding Belarusian TTS model by @erogol in https://github.com/coqui-ai/TTS/pull/2922
Tortoise inference fix and fix zoo unit tests by @Edresson in https://github.com/coqui-ai/TTS/pull/3010

New Contributors

@akx made their first contribution in https://github.com/coqui-ai/TTS/pull/3003

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.17.5...v0.17.6

- Python
Published by erogol over 2 years ago

tts - v0.17.5

What's Changed

Fix fsspec requirement by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2970
Add coqui blog post by @osanseviero in https://github.com/coqui-ai/TTS/pull/2949
fix: xtts not taking into account device flag by @loupzeur in https://github.com/coqui-ai/TTS/pull/2951
fix package versions by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2990

New Contributors

@osanseviero made their first contribution in https://github.com/coqui-ai/TTS/pull/2949
@loupzeur made their first contribution in https://github.com/coqui-ai/TTS/pull/2951

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.17.4...v0.17.5

- Python
Published by erogol over 2 years ago

tts - v0.17.4

Identical to v0.17.3 - retriggered due to failed CI and missing package on PyPI

- Python
Published by reuben over 2 years ago

tts - v0.17.3

You can set COQUI_TOS_AGREED=1 to pass the ToS when using XTTS

- Python
Published by erogol over 2 years ago

tts - v0.17.2

What's Changed

Fix model tests by @erogol in https://github.com/coqui-ai/TTS/pull/2943

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.17.1...v0.17.2

- Python
Published by erogol over 2 years ago

tts - v0.17.1

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.17.0...v0.17.1

- Python
Published by erogol over 2 years ago

tts - 👑v0.17.0

What's Changed

👑XTTS implementation by @erogol in https://github.com/coqui-ai/TTS/pull/2939
Fix requests exception handling in manage.py by @Cohee1207 in https://github.com/coqui-ai/TTS/pull/2912
Fixed spectrogram checking on librosa 0.10.x by @T145 in https://github.com/coqui-ai/TTS/pull/2899
Add CML-TTS dataset YourTTS training recipe by @Edresson in https://github.com/coqui-ai/TTS/pull/2934

New Contributors

@Cohee1207 made their first contribution in https://github.com/coqui-ai/TTS/pull/2912
@T145 made their first contribution in https://github.com/coqui-ai/TTS/pull/2899

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.16.6...v0.17.0

What's Changed

Fix requests exception handling in manage.py by @Cohee1207 in https://github.com/coqui-ai/TTS/pull/2912
Fixed spectrogram checking on librosa 0.10.x by @T145 in https://github.com/coqui-ai/TTS/pull/2899
Add CML-TTS dataset YourTTS training recipe by @Edresson in https://github.com/coqui-ai/TTS/pull/2934

New Contributors

@Cohee1207 made their first contribution in https://github.com/coqui-ai/TTS/pull/2912
@T145 made their first contribution in https://github.com/coqui-ai/TTS/pull/2899

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.16.6...v0.17.0

- Python
Published by erogol over 2 years ago

tts - v0.16.6

What's Changed

Update README with new device API by @jaketae in https://github.com/coqui-ai/TTS/pull/2876
Add device flag to TTS CLI by @jaketae in https://github.com/coqui-ai/TTS/pull/2875
[WIP] Add phonemizer for Belarusian language by @alex73 in https://github.com/coqui-ai/TTS/pull/2856
Updated scipy version by @Exponefrv1 in https://github.com/coqui-ai/TTS/pull/2914
Update docs by @erogol in https://github.com/coqui-ai/TTS/pull/2919

New Contributors

@Exponefrv1 made their first contribution in https://github.com/coqui-ai/TTS/pull/2914

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.16.5...v0.16.6

- Python
Published by erogol over 2 years ago

tts - v0.16.5

What's Changed

Fix loading Bark by @erogol in https://github.com/coqui-ai/TTS/pull/2893

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.16.4...v0.16.5

- Python
Published by erogol over 2 years ago

tts - v0.16.4

What's Changed

Add customizable data home path by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2871
Add device support in TTS and Synthesizer by @jaketae in https://github.com/coqui-ai/TTS/pull/2855

New Contributors

@jaketae made their first contribution in https://github.com/coqui-ai/TTS/pull/2855

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.16.3...v0.16.4

- Python
Published by erogol over 2 years ago

tts - v0.16.3

What's Changed

Update Studio API for XTTS by @erogol in https://github.com/coqui-ai/TTS/pull/2861
Denote human voices in README.md by @michaelnew in https://github.com/coqui-ai/TTS/pull/2851

New Contributors

@michaelnew made their first contribution in https://github.com/coqui-ai/TTS/pull/2851

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.16.2...v0.16.3

- Python
Published by erogol over 2 years ago

tts - v0.16.2

What's Changed

add post functionality to /api/tts by @ChaseCares in https://github.com/coqui-ai/TTS/pull/2836
Add fairseq onnx support and strict configuration, fixes some onnx errors by @SystemPanic in https://github.com/coqui-ai/TTS/pull/2831
Fix phoneme coverage notebook imports by @erogol in https://github.com/coqui-ai/TTS/pull/2845
Handle missing JA phonemizer by @erogol in https://github.com/coqui-ai/TTS/pull/2843

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.16.1...v0.16.2

- Python
Published by erogol over 2 years ago

tts - v0.16.1

What's Changed

Adds multi-language support for VITS onnx, fixes onnx exporting and inference errors by @SystemPanic in https://github.com/coqui-ai/TTS/pull/2816
Recipe for Belarusian TTS by @alex73 in https://github.com/coqui-ai/TTS/pull/2756
Delightful TTS VCTK recipe fixes by @AWAS666 in https://github.com/coqui-ai/TTS/pull/2808
Add kwargs to ignore extra arguments w/o error by @erogol in https://github.com/coqui-ai/TTS/pull/2822
Fix DelightfulTTS by @erogol in https://github.com/coqui-ai/TTS/pull/2823

New Contributors

@SystemPanic made their first contribution in https://github.com/coqui-ai/TTS/pull/2816
@AWAS666 made their first contribution in https://github.com/coqui-ai/TTS/pull/2808

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.16.0...v0.16.1

- Python
Published by erogol over 2 years ago

tts - v0.16.0

What's Changed

Fix #2749 by @erogol in https://github.com/coqui-ai/TTS/pull/2750
Fix share model page URL by @alex73 in https://github.com/coqui-ai/TTS/pull/2757
Make Japanese-specific dependencies optional by @polm in https://github.com/coqui-ai/TTS/pull/2776
API tests by @erogol in https://github.com/coqui-ai/TTS/pull/2790
Add Delightful-TTS model by @loganhart420 in https://github.com/coqui-ai/TTS/pull/2095
Fix Tortoise load by @erogol in https://github.com/coqui-ai/TTS/pull/2791

New Contributors

@alex73 made their first contribution in https://github.com/coqui-ai/TTS/pull/2757
@polm made their first contribution in https://github.com/coqui-ai/TTS/pull/2776

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.15.6...v0.16.0

- Python
Published by erogol over 2 years ago

tts - 🛠️v0.15.6

What's Changed

fix loading of model and vocoder configs by @ChaseCares in https://github.com/coqui-ai/TTS/pull/2698
Update compute_embeddings.py by @46319943 in https://github.com/coqui-ai/TTS/pull/2668
delete meaningless print() by @ZhouGongZaiShi in https://github.com/coqui-ai/TTS/pull/2662
fixed small spelling mistakes finetuning.md by @Woutervdvelde in https://github.com/coqui-ai/TTS/pull/2551
Resolve conflicts by @erogol in https://github.com/coqui-ai/TTS/pull/2741
Export multispeaker onnx by @erogol in https://github.com/coqui-ai/TTS/pull/2743
Fix #2745 by @erogol in https://github.com/coqui-ai/TTS/pull/2748

New Contributors

@ChaseCares made their first contribution in https://github.com/coqui-ai/TTS/pull/2698
@46319943 made their first contribution in https://github.com/coqui-ai/TTS/pull/2668
@ZhouGongZaiShi made their first contribution in https://github.com/coqui-ai/TTS/pull/2662
@Woutervdvelde made their first contribution in https://github.com/coqui-ai/TTS/pull/2551

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.15.5...v0.15.6

- Python
Published by erogol over 2 years ago

tts - 🛠️ v0.15.5

What's Changed

Update docs and credits by @erogol in https://github.com/coqui-ai/TTS/pull/2733

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.15.4...v0.15.5

- Python
Published by erogol over 2 years ago

tts - 🛠️v0.15.4

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.15.2...v0.15.4

- Python
Published by erogol over 2 years ago

tts - 🛠️v0.15.2

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.15.1...v0.15.2

- Python
Published by erogol over 2 years ago

tts - 🛠️v0.15.1

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.15.0...v0.15.1

Fix docs

- Python
Published by erogol over 2 years ago

tts - 😄 v0.15.0

What's Changed

Update stochasticdurationpredictor.py by @mengting7tw in https://github.com/coqui-ai/TTS/pull/2663
Fix Tortoise load by @erogol in https://github.com/coqui-ai/TTS/pull/2697
Inference API for 🐶Bark by @erogol in https://github.com/coqui-ai/TTS/pull/2685
Drop Python 3.7 and 3.8 and stage Python 3.11 by @erogol in https://github.com/coqui-ai/TTS/pull/2700

Running 🐶Bark

```python text = "Hello, my name is Manmay , how are you?"

from TTS.tts.configs.bark_config import BarkConfig from TTS.tts.models.bark import Bark

config = BarkConfig() model = Bark.initfromconfig(config) model.loadcheckpoint(config, checkpointdir="path/to/model/dir/", eval=True)

with random speaker

outputdict = model.synthesize(text, config, speakerid="random", voice_dirs=None)

cloning a speaker.

It assumes that you have a speaker file in `bark_voices/speaker_n/speaker.wav` or `bark_voices/speaker_n/speaker.npz`

outputdict = model.synthesize(text, config, speakerid="ljspeech", voicedirs="barkvoices/") ```

Using 🐸TTS API:

```python from TTS.api import TTS

Load the model to GPU

Bark is really slow on CPU, so we recommend using GPU.

tts = TTS("tts_models/multilingual/multi-dataset/bark", gpu=True)

Cloning a new speaker

This expects to find a mp3 or wav file like `bark_voices/new_speaker/speaker.wav`

It computes the cloning values and stores in `bark_voices/new_speaker/speaker.npz`

tts.ttstofile(text="Hello, my name is Manmay , how are you?", filepath="output.wav", voicedir="bark_voices/", speaker="ljspeech")

When you run it again it uses the stored values to generate the voice.

tts.ttstofile(text="Hello, my name is Manmay , how are you?", filepath="output.wav", voicedir="bark_voices/", speaker="ljspeech")

random speaker

tts = TTS("ttsmodels/multilingual/multi-dataset/bark", gpu=True) tts.ttstofile("hello world", filepath="out.wav") ```

Using 🐸TTS Command line:

```console

cloning the `ljspeech` voice

tts --modelname ttsmodels/multilingual/multi-dataset/bark \ --text "This is an example." \ --outpath "output.wav" \ --voicedir barkvoices/ \ --speakeridx "ljspeech" \ --progress_bar True

Random voice generation

tts --modelname ttsmodels/multilingual/multi-dataset/bark \ --text "This is an example." \ --outpath "output.wav" \ --progressbar True ```

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.14.3...v0.15.0

- Python
Published by erogol over 2 years ago

tts - 👉 v0.14.3

- Python
Published by erogol over 2 years ago

tts - ⛈️ v0.14.2

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.14.1...v0.14.2

- Python
Published by erogol over 2 years ago

tts - 🚗 v0.14.1

What's Changed

Fetch all built-in speakers from API by @reuben in https://github.com/coqui-ai/TTS/pull/2626
fix typo by @vodiylik in https://github.com/coqui-ai/TTS/pull/2647
Port Fairseq TTS models by @erogol in https://github.com/coqui-ai/TTS/pull/2628

New Contributors

@vodiylik made their first contribution in https://github.com/coqui-ai/TTS/pull/2647

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.14.0...v0.14.1

Example text to speech using Fairseq models in ~1100 languages 🤯.

For these models use the following name format: tts_models/<lang-iso_code>/fairseq/vits.

You can find the list of language ISO codes here and learn about the Fairseq models here.

```python from TTS.api import TTS api = TTS(modelname="ttsmodels/eng/fairseq/vits", gpu=True) api.ttstofile("This is a test.", file_path="output.wav")

TTS with on the fly voice conversion

api = TTS("ttsmodels/deu/fairseq/vits") api.ttswithvctofile( "Wie sage ich auf Italienisch, dass ich dich liebe?", speakerwav="target/speaker.wav", file_path="ouptut.wav" ) ```

- Python
Published by erogol over 2 years ago

tts - v0.14.0

What's Changed

Typos and minor fixes by @prakharpbuf in https://github.com/coqui-ai/TTS/pull/2508
Add FR and ES gruut languages as requirement to avoid inference issues by @Edresson in https://github.com/coqui-ai/TTS/pull/2572
Lighter docker image by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2600
Use default_factory for audio parameter by @v4hn in https://github.com/coqui-ai/TTS/pull/2576
Update README.md by @HighnessAtharva in https://github.com/coqui-ai/TTS/pull/2577
Add Jenny model by @erogol in https://github.com/coqui-ai/TTS/pull/2603
Warn when lang is not avail by @erogol in https://github.com/coqui-ai/TTS/pull/2460
Update VAD for silence trimming. by @erogol in https://github.com/coqui-ai/TTS/pull/2604
Tortoise TTS inference by @manmay-nakhashi in https://github.com/coqui-ai/TTS/pull/2547
Draft ONNX export for VITS by @erogol in https://github.com/coqui-ai/TTS/pull/2563

New Contributors

@prakharpbuf made their first contribution in https://github.com/coqui-ai/TTS/pull/2508
@v4hn made their first contribution in https://github.com/coqui-ai/TTS/pull/2576
@HighnessAtharva made their first contribution in https://github.com/coqui-ai/TTS/pull/2577

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.13.3...v0.14.0

- Python
Published by erogol almost 3 years ago

tts - v0.14.0_models

Jenny VITS model trained by 👑@noml4u

bash tts --model_name tts_models/en/jenny/jenny --text "This is a test. This is also a test."

- Python
Published by erogol almost 3 years ago

tts - v0.14.1_models

- Python
Published by erogol almost 3 years ago

tts - 🐶 v0.13.3

What's Changed

Bangla models by @erogol in https://github.com/coqui-ai/TTS/pull/2532

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.13.2...v0.13.3

- Python
Published by erogol almost 3 years ago

tts - v0.13.3_models

Single speaker Bangla Male/Female models

These are single-speaker VITS models with a 22050hz sampling rate.

By 👑 @mobassir94 Original repo: https://github.com/mobassir94/comprehensive-bangla-tts

Male Model

shell tts --model_name tts_models/bn/custom/vits-male --text "এটি ডেমো করার উদ্দেশ্যে একটি ডেমো"

```python from TTS.api import TTS

tts = TTS(modelname="ttsmodels/bn/custom/vits-male") tts.ttstofile(text="এটি ডেমো করার উদ্দেশ্যে একটি ডেমো", file_path="output.wav")

TTS with voice conversion to a reference speaker in `target_speaker.wav`

ttswithvctofile(text="এটি ডেমো করার উদ্দেশ্যে একটি ডেমো", speakerwav="targetspeaker.wav", file_path="output.wav") ```

Female Model

shell tts --model_name tts_models/bn/custom/vits-female --text "এটি ডেমো করার উদ্দেশ্যে একটি ডেমো"

```python from TTS.api import TTS

tts = TTS(modelname="ttsmodels/bn/custom/vits-female") tts.ttstofile(text="এটি ডেমো করার উদ্দেশ্যে একটি ডেমো", file_path="output.wav")

TTS with voice conversion to a reference speaker in `target_speaker.wav`

ttswithvctofile(text="এটি ডেমো করার উদ্দেশ্যে একটি ডেমো", speakerwav="targetspeaker.wav", file_path="output.wav") ```

- Python
Published by erogol almost 3 years ago

tts - 🌈v0.13.2

What's Changed

🐸Studio models by tts by @erogol in https://github.com/coqui-ai/TTS/pull/2515
Update VAD by @erogol in https://github.com/coqui-ai/TTS/pull/2509
🌈 v0.13.2 by @erogol in https://github.com/coqui-ai/TTS/pull/2519

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.13.1...v0.13.2

- Python
Published by erogol almost 3 years ago

tts - v0.13.1

What's Changed

Update Librosa Version To V0.10.0 by @MattyB95 in https://github.com/coqui-ai/TTS/pull/2480
Api voice conversion by @erogol in https://github.com/coqui-ai/TTS/pull/2495
✨ v0.13.1 by @erogol in https://github.com/coqui-ai/TTS/pull/2499

New Contributors

@MattyB95 made their first contribution in https://github.com/coqui-ai/TTS/pull/2480

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.13.0...v0.13.1

- Python
Published by erogol almost 3 years ago

tts - v0.13.0

What's Changed

vits.py training fixed due to return_complex by @iamkhalidbashir in https://github.com/coqui-ai/TTS/pull/2418
Update numba version by @erogol in https://github.com/coqui-ai/TTS/pull/2435
Implement FreeVC by @erogol in https://github.com/coqui-ai/TTS/pull/2451
[minor] hifigan_generator.py typo by @p0p4k in https://github.com/coqui-ai/TTS/pull/2462
[minor] batch["speaker_ids"] getting set two times by @p0p4k in https://github.com/coqui-ai/TTS/pull/2470
fix typo by @BenoitWang in https://github.com/coqui-ai/TTS/pull/2475
Fixes typo in README.md example code by @TCNOco in https://github.com/coqui-ai/TTS/pull/2478
🐸 Coqui Studio API integration by @erogol in https://github.com/coqui-ai/TTS/pull/2484

New Contributors

@BenoitWang made their first contribution in https://github.com/coqui-ai/TTS/pull/2475
@TCNOco made their first contribution in https://github.com/coqui-ai/TTS/pull/2478

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.12.0...v0.13.0

- Python
Published by erogol almost 3 years ago

tts - FreeVC Models

Landed with v0.12.0

- Python
Published by erogol almost 3 years ago

tts - v0.12.0

What's Changed

numpy version for py310 by @p0p4k in https://github.com/coqui-ai/TTS/pull/2316
Fix Speaker Consistency Loss (SCL) by @Edresson in https://github.com/coqui-ai/TTS/pull/2364
OverFlow with test sentences by @thennal10 in https://github.com/coqui-ai/TTS/pull/2253
Basic Mary-TTS API compatibility by @fquirin in https://github.com/coqui-ai/TTS/pull/2352
add energy by default to Fastspeech2 config by @manmay-nakhashi in https://github.com/coqui-ai/TTS/pull/2326
Remove doc bot by @erogol in https://github.com/coqui-ai/TTS/pull/2399
Update docs by @erogol in https://github.com/coqui-ai/TTS/pull/2389
v0.12.0 by @erogol in https://github.com/coqui-ai/TTS/pull/2390

New Contributors

@thennal10 made their first contribution in https://github.com/coqui-ai/TTS/pull/2253
@fquirin made their first contribution in https://github.com/coqui-ai/TTS/pull/2352

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.11.1...v0.12.0

- Python
Published by erogol almost 3 years ago

tts - v0.11.1

What's Changed

Add pre-trained NeuralHMM model by @erogol in https://github.com/coqui-ai/TTS/pull/2314
v0.11.1 by @erogol in https://github.com/coqui-ai/TTS/pull/2339

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.11.0...v0.11.1

- Python
Published by erogol about 3 years ago

tts - v0.11.0

What's Changed

v0.9.0 by @erogol in https://github.com/coqui-ai/TTS/pull/1942
🚀 v0.10.0 by @erogol in https://github.com/coqui-ai/TTS/pull/2205
v0.10.1 by @erogol in https://github.com/coqui-ai/TTS/pull/2242
Fastspeech2 by @manmay-nakhashi in https://github.com/coqui-ai/TTS/pull/2073
Cache speaker encoder model by @erogol in https://github.com/coqui-ai/TTS/pull/2284
Adding neural HMM TTS Model by @shivammehta25 in https://github.com/coqui-ai/TTS/pull/2272
Add Catalan text cleaners for Catalan support by @GerrySant in https://github.com/coqui-ai/TTS/pull/2295
Use packaging.version for version comparisons by @mweinelt in https://github.com/coqui-ai/TTS/pull/2310
Fix tts-server for multi-lingual models by @marius851000 in https://github.com/coqui-ai/TTS/pull/2257
API from model path by @erogol in https://github.com/coqui-ai/TTS/pull/2303
v0.11.0 by @erogol in https://github.com/coqui-ai/TTS/pull/2277
v0.11.0 by @erogol in https://github.com/coqui-ai/TTS/pull/2328
Bump up to v0.11.0 by @erogol in https://github.com/coqui-ai/TTS/pull/2329
v0.11.0 (#2329) by @erogol in https://github.com/coqui-ai/TTS/pull/2337

New Contributors

@GerrySant made their first contribution in https://github.com/coqui-ai/TTS/pull/2295
@mweinelt made their first contribution in https://github.com/coqui-ai/TTS/pull/2310
@marius851000 made their first contribution in https://github.com/coqui-ai/TTS/pull/2257

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.10.2...v0.11.0

- Python
Published by erogol about 3 years ago

tts - v0.11.0_models

NeuralHMM trained on LJSpeech by 👑 @shivammehta25

- Python
Published by erogol about 3 years ago

tts - v0.10.2

What's Changed

Multilingual tokenizer by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2229
Fixed bug related to yourtts speaker embeddings issue by @iamkhalidbashir in https://github.com/coqui-ai/TTS/pull/2234
Update the Trainer requirement version for a compatible one by @Edresson in https://github.com/coqui-ai/TTS/pull/2276

New Contributors

@iamkhalidbashir made their first contribution in https://github.com/coqui-ai/TTS/pull/2234

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.10.1...v0.10.2

- Python
Published by erogol about 3 years ago

tts - v0.10.1

What's Changed

fixed tutorial 2 incompatibility with new dev by @Aya-AlJafari in https://github.com/coqui-ai/TTS/pull/2161
Fix capacitron test when cuda is enabled by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2189
Fix VITS multi-speaker voice conversion inference by @Edresson in https://github.com/coqui-ai/TTS/pull/2187
Handle espeak 1.48.15 by @erogol in https://github.com/coqui-ai/TTS/pull/2203
Python API implementation by @erogol in https://github.com/coqui-ai/TTS/pull/2195
Update README by @erogol in https://github.com/coqui-ai/TTS/pull/2204
Update formatters.py by @p0p4k in https://github.com/coqui-ai/TTS/pull/2194
Adding OverFlow by @shivammehta25 in https://github.com/coqui-ai/TTS/pull/2183
Add YourTTS VCTK recipe by @Edresson in https://github.com/coqui-ai/TTS/pull/2198
Add Original YourTTS vocabulary on YourTTS recipe for full transfer learning by @Edresson in https://github.com/coqui-ai/TTS/pull/2206
Adding pre-trained Overflow model by @erogol in https://github.com/coqui-ai/TTS/pull/2211
Fixup overflow by @erogol in https://github.com/coqui-ai/TTS/pull/2218
Add Ukrainian LADA (female) voice by @egorsmkv in https://github.com/coqui-ai/TTS/pull/2226

New Contributors

@shivammehta25 made their first contribution in https://github.com/coqui-ai/TTS/pull/2183
@egorsmkv made their first contribution in https://github.com/coqui-ai/TTS/pull/2226

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.9.0...v0.10.1

- Python
Published by erogol about 3 years ago

tts - v0.10.1_models

This release includes 3 new models

Multilingual YourTTS updated version based on the recent recipe.
Catalan multi-speaker VITS model by 👑@gullabi

console tts --model_name tts_models/ca/custom/vits --text "Ei, com estàs avui? Us desitjo unes bones festes." --speaker_idx d0cd44fcdae652efb0dd428cd1b8f1911e6eb2ca3469a1f2d6f9faf97a9d05e30f28387dfb81bfb4c97eba64187a0c047c85bf06998ccaec58781f3982626bb6 Note: Speaker names are quite long 😄 for this model - Parsian single-speaker female GlowTTS model by 👑@karim23657 (without compatible vocoder)

console tts --model_name tts_models/fa/custom/glow-tts --text "سلام امروز چطوری؟ تعطیلات خوشی را برای شما آرزو می کنم."

- Python
Published by erogol about 3 years ago

tts - v0.10.0

What's Changed

v0.9.0 by @erogol in https://github.com/coqui-ai/TTS/pull/1942
fixed tutorial 2 incompatibility with new dev by @Aya-AlJafari in https://github.com/coqui-ai/TTS/pull/2161
Fix capacitron test when cuda is enabled by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2189
Fix VITS multi-speaker voice conversion inference by @Edresson in https://github.com/coqui-ai/TTS/pull/2187
Handle espeak 1.48.15 by @erogol in https://github.com/coqui-ai/TTS/pull/2203
Python API implementation by @erogol in https://github.com/coqui-ai/TTS/pull/2195
Update README by @erogol in https://github.com/coqui-ai/TTS/pull/2204
Update formatters.py by @p0p4k in https://github.com/coqui-ai/TTS/pull/2194
Adding OverFlow by @shivammehta25 in https://github.com/coqui-ai/TTS/pull/2183
Add YourTTS VCTK recipe by @Edresson in https://github.com/coqui-ai/TTS/pull/2198
Add Original YourTTS vocabulary on YourTTS recipe for full transfer learning by @Edresson in https://github.com/coqui-ai/TTS/pull/2206
Adding pre-trained Overflow model by @erogol in https://github.com/coqui-ai/TTS/pull/2211
Fixup overflow by @erogol in https://github.com/coqui-ai/TTS/pull/2218
🚀 v0.10.0 by @erogol in https://github.com/coqui-ai/TTS/pull/2205

New Contributors

@shivammehta25 made their first contribution in https://github.com/coqui-ai/TTS/pull/2183

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.9.0...v0.10.0

- Python
Published by erogol about 3 years ago

tts - v0.10.0_models

Overflow model trained on LJSpeech dataset using pretrained HifiGAN vocoder vocoder_models/en/ljspeech/hifigan_v2.

- Python
Published by erogol about 3 years ago

tts - v0.9.0

New models

Added 25 new models covering 25 different EU languages from 👑https://github.com/NeonGeckoCom/neon-tts-plugin-coqui

What's Changed

Trick to Upsampling to High sampling rates using VITS model by @Edresson in https://github.com/coqui-ai/TTS/pull/1456
Update Coqpit requirement by @Edresson in https://github.com/coqui-ai/TTS/pull/1539
Missing f prefix on f-strings fix by @code-review-doctor in https://github.com/coqui-ai/TTS/pull/1532
tiny improvement in data_path resolvement by @taras-sereda in https://github.com/coqui-ai/TTS/pull/1567
Fix VITS upsampling asserts by @Edresson in https://github.com/coqui-ai/TTS/pull/1550
Fix the bug in eSpeak wrapper for eSpeak version 1.48.15 by @Edresson in https://github.com/coqui-ai/TTS/pull/1560
🐍 Python 3.10.x support and drop Python 3.6 support by @erogol in https://github.com/coqui-ai/TTS/pull/1565
Update CI tests by @erogol in https://github.com/coqui-ai/TTS/pull/1572
Build and publish CPU only Docker image by @erogol in https://github.com/coqui-ai/TTS/pull/1573
Add an assert for the upsampling trick by @erogol in https://github.com/coqui-ai/TTS/pull/1538
Add audio length sampler balancer by @Edresson in https://github.com/coqui-ai/TTS/pull/1561
Change the VITS upsampling interpolation trick to linear by @Edresson in https://github.com/coqui-ai/TTS/pull/1564
Capacitron by @a-froghyar in https://github.com/coqui-ai/TTS/pull/977
Fixed usecuda issue in computeembeddings.py by @ribeiromiranda in https://github.com/coqui-ai/TTS/pull/1587
Training recipes for thorsten dataset by @noranraskin in https://github.com/coqui-ai/TTS/pull/1020
fix invalid json by @s3781009 in https://github.com/coqui-ai/TTS/pull/1599
Use fsspec and torch for embedding file IO by @erogol in https://github.com/coqui-ai/TTS/pull/1581
Adding TTS Tutorials by @Aya-AlJafari in https://github.com/coqui-ai/TTS/pull/1584
Internal formatter by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1629
Update trainingamodel.md by @klotlabs in https://github.com/coqui-ai/TTS/pull/1620
Add synpaflex formatter by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1616
added support for model_info in CLI by @p0p4k in https://github.com/coqui-ai/TTS/pull/1623
Add Thorsten VITS model by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1675
Checkpoint bug fix by @manmay-nakhashi in https://github.com/coqui-ai/TTS/pull/1641
docs : Adding in the arguments for CLI by @camillem in https://github.com/coqui-ai/TTS/pull/1469
Fix Publish CI by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1597
Fix tokenizer for punc only by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1717
Add durations as aux input for VITS by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1694
feat: updated capacitron recipes and lr fix by @a-froghyar in https://github.com/coqui-ai/TTS/pull/1718
Implement VitsAudioConfig by @erogol in https://github.com/coqui-ai/TTS/pull/1556
Fix aux tests by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1753
Fix for FloorDiv Function Warning by @iprovalo in https://github.com/coqui-ai/TTS/pull/1760
Update download_vctk.sh by @mengting7tw in https://github.com/coqui-ai/TTS/pull/1739
Update decoder.py by @p0p4k in https://github.com/coqui-ai/TTS/pull/1792
Update requirements.txt for python 3.10 support by @p0p4k in https://github.com/coqui-ai/TTS/pull/1791
Update README.md by @yuripourre in https://github.com/coqui-ai/TTS/pull/1776
Fix & update WaveRNN vocoder model by @vanIvan in https://github.com/coqui-ai/TTS/pull/1749
Update requirements.txt; inflect==5.6 by @p0p4k in https://github.com/coqui-ai/TTS/pull/1809
Update README.md; download progress bar in CLI. by @p0p4k in https://github.com/coqui-ai/TTS/pull/1797
Update wavenet.py by @p0p4k in https://github.com/coqui-ai/TTS/pull/1796
Adjust default to be able to process longer sentences by @lkiesow in https://github.com/coqui-ai/TTS/pull/1835
Fix language flags generated by espeak-ng phonemizer by @Lokhozt in https://github.com/coqui-ai/TTS/pull/1801
fix getrandomembeddings --> getrandomembedding by @manmay-nakhashi in https://github.com/coqui-ai/TTS/pull/1726
Introduce numpy and torch transforms by @erogol in https://github.com/coqui-ai/TTS/pull/1705
Implement bucketed weighted sampling for VITS by @erogol in https://github.com/coqui-ai/TTS/pull/1871
capacitron_layers multi speaker bug fix by @manmay-nakhashi in https://github.com/coqui-ai/TTS/pull/1664
updates to dataset analysis notebooks by @jreus in https://github.com/coqui-ai/TTS/pull/1853
Fix BCE loss issue by @erogol in https://github.com/coqui-ai/TTS/pull/1872
Remove deprecated files by @erogol in https://github.com/coqui-ai/TTS/pull/1873
Handle when no batch sampler by @erogol in https://github.com/coqui-ai/TTS/pull/1882
Fix tune wavegrad by @geth-network in https://github.com/coqui-ai/TTS/pull/1844
Add new DE Thorsten models by @erogol in https://github.com/coqui-ai/TTS/pull/1898
Add speaker encoder recipe by @Edresson in https://github.com/coqui-ai/TTS/pull/1912
Add capacitron v2 model by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1768
Fixes a race condition with multiple simultaneous get requests. by @KyuubiYoru in https://github.com/coqui-ai/TTS/pull/1807
Fix find unique phonemes script by @Edresson in https://github.com/coqui-ai/TTS/pull/1928
Add YourTTS and SC-GlowTTS on available models by @Edresson in https://github.com/coqui-ai/TTS/pull/1933
Korean Phonemizer by @harmlessman in https://github.com/coqui-ai/TTS/pull/1822
Add espeak support for Chinese by @happylittlecat2333 in https://github.com/coqui-ai/TTS/pull/1905
Replace pyworld by pyin by @Edresson in https://github.com/coqui-ai/TTS/pull/1946
d-vector handling by @erogol in https://github.com/coqui-ai/TTS/pull/1945
Fixups by @erogol in https://github.com/coqui-ai/TTS/pull/1967
Fix VC by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1971
Update readme by @erogol in https://github.com/coqui-ai/TTS/pull/1978
Add metafile arg to compute embeddings script by @erogol in https://github.com/coqui-ai/TTS/pull/1977
Fix dataset handling with the new embedding file keys by @Edresson in https://github.com/coqui-ai/TTS/pull/1991
Fix colliding dataset cache file names by @Edresson in https://github.com/coqui-ai/TTS/pull/1994
Write non-speech files in a TXT by @erogol in https://github.com/coqui-ai/TTS/pull/2048
Minor bug fixes on VITS/YourTTS and inference by @Edresson in https://github.com/coqui-ai/TTS/pull/2054
Check num of columns in coqui format by @erogol in https://github.com/coqui-ai/TTS/pull/2066
Remove / prefix from the relative path by @erogol in https://github.com/coqui-ai/TTS/pull/2065
Update Tutorial2trainyourfirstTTSmodel.ipynb by @CeadeS in https://github.com/coqui-ai/TTS/pull/2079
Update forward_tts.md by @mrshu in https://github.com/coqui-ai/TTS/pull/2019
Use "formatter" key in the datasets json array by @humada05 in https://github.com/coqui-ai/TTS/pull/2114
capacitron training fixes by @victor-shepardson in https://github.com/coqui-ai/TTS/pull/2086
mailabs formatter: back/forward slash in file path fix by @freezerain in https://github.com/coqui-ai/TTS/pull/1938
Add Discord server badge by @erogol in https://github.com/coqui-ai/TTS/pull/2136
Remove langs expect en and de by @erogol in https://github.com/coqui-ai/TTS/pull/2135
Cache fsspec downloaded files by @erogol in https://github.com/coqui-ai/TTS/pull/2132
Update dep caching in actions by @erogol in https://github.com/coqui-ai/TTS/pull/2138
Update README.md by @eltociear in https://github.com/coqui-ai/TTS/pull/2146
Makes docker images lighter by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2149
Doc update docker by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2153
Add neon models by @loganhart420 in https://github.com/coqui-ai/TTS/pull/2140
Fix documentation by @WeberJulian in https://github.com/coqui-ai/TTS/pull/2154

New Contributors

@code-review-doctor made their first contribution in https://github.com/coqui-ai/TTS/pull/1532
@taras-sereda made their first contribution in https://github.com/coqui-ai/TTS/pull/1567
@ribeiromiranda made their first contribution in https://github.com/coqui-ai/TTS/pull/1587
@s3781009 made their first contribution in https://github.com/coqui-ai/TTS/pull/1599
@Aya-AlJafari made their first contribution in https://github.com/coqui-ai/TTS/pull/1584
@klotlabs made their first contribution in https://github.com/coqui-ai/TTS/pull/1620
@p0p4k made their first contribution in https://github.com/coqui-ai/TTS/pull/1623
@manmay-nakhashi made their first contribution in https://github.com/coqui-ai/TTS/pull/1641
@camillem made their first contribution in https://github.com/coqui-ai/TTS/pull/1469
@iprovalo made their first contribution in https://github.com/coqui-ai/TTS/pull/1760
@mengting7tw made their first contribution in https://github.com/coqui-ai/TTS/pull/1739
@yuripourre made their first contribution in https://github.com/coqui-ai/TTS/pull/1776
@vanIvan made their first contribution in https://github.com/coqui-ai/TTS/pull/1749
@lkiesow made their first contribution in https://github.com/coqui-ai/TTS/pull/1835
@Lokhozt made their first contribution in https://github.com/coqui-ai/TTS/pull/1801
@jreus made their first contribution in https://github.com/coqui-ai/TTS/pull/1853
@geth-network made their first contribution in https://github.com/coqui-ai/TTS/pull/1844
@KyuubiYoru made their first contribution in https://github.com/coqui-ai/TTS/pull/1807
@harmlessman made their first contribution in https://github.com/coqui-ai/TTS/pull/1822
@happylittlecat2333 made their first contribution in https://github.com/coqui-ai/TTS/pull/1905
@CeadeS made their first contribution in https://github.com/coqui-ai/TTS/pull/2079
@mrshu made their first contribution in https://github.com/coqui-ai/TTS/pull/2019
@humada05 made their first contribution in https://github.com/coqui-ai/TTS/pull/2114
@victor-shepardson made their first contribution in https://github.com/coqui-ai/TTS/pull/2086
@freezerain made their first contribution in https://github.com/coqui-ai/TTS/pull/1938
@eltociear made their first contribution in https://github.com/coqui-ai/TTS/pull/2146

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.6.2...v0.9.0

- Python
Published by erogol over 3 years ago

tts - v0.8.0

What's Changed

Trick to Upsampling to High sampling rates using VITS model by @Edresson in https://github.com/coqui-ai/TTS/pull/1456
Update Coqpit requirement by @Edresson in https://github.com/coqui-ai/TTS/pull/1539
Missing f prefix on f-strings fix by @code-review-doctor in https://github.com/coqui-ai/TTS/pull/1532
tiny improvement in data_path resolvement by @taras-sereda in https://github.com/coqui-ai/TTS/pull/1567
Fix VITS upsampling asserts by @Edresson in https://github.com/coqui-ai/TTS/pull/1550
Fix the bug in eSpeak wrapper for eSpeak version 1.48.15 by @Edresson in https://github.com/coqui-ai/TTS/pull/1560
🐍 Python 3.10.x support and drop Python 3.6 support by @erogol in https://github.com/coqui-ai/TTS/pull/1565
Update CI tests by @erogol in https://github.com/coqui-ai/TTS/pull/1572
Build and publish CPU only Docker image by @erogol in https://github.com/coqui-ai/TTS/pull/1573
Add an assert for the upsampling trick by @erogol in https://github.com/coqui-ai/TTS/pull/1538
Add audio length sampler balancer by @Edresson in https://github.com/coqui-ai/TTS/pull/1561
Change the VITS upsampling interpolation trick to linear by @Edresson in https://github.com/coqui-ai/TTS/pull/1564
Capacitron by @a-froghyar in https://github.com/coqui-ai/TTS/pull/977
Fixed usecuda issue in computeembeddings.py by @ribeiromiranda in https://github.com/coqui-ai/TTS/pull/1587
Training recipes for thorsten dataset by @noranraskin in https://github.com/coqui-ai/TTS/pull/1020
fix invalid json by @s3781009 in https://github.com/coqui-ai/TTS/pull/1599
Use fsspec and torch for embedding file IO by @erogol in https://github.com/coqui-ai/TTS/pull/1581
Adding TTS Tutorials by @Aya-AlJafari in https://github.com/coqui-ai/TTS/pull/1584
Internal formatter by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1629
Update trainingamodel.md by @klotlabs in https://github.com/coqui-ai/TTS/pull/1620
Add synpaflex formatter by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1616
added support for model_info in CLI by @p0p4k in https://github.com/coqui-ai/TTS/pull/1623
Add Thorsten VITS model by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1675
Checkpoint bug fix by @manmay-nakhashi in https://github.com/coqui-ai/TTS/pull/1641
docs : Adding in the arguments for CLI by @camillem in https://github.com/coqui-ai/TTS/pull/1469
Fix Publish CI by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1597
Fix tokenizer for punc only by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1717
Add durations as aux input for VITS by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1694
feat: updated capacitron recipes and lr fix by @a-froghyar in https://github.com/coqui-ai/TTS/pull/1718
Implement VitsAudioConfig by @erogol in https://github.com/coqui-ai/TTS/pull/1556
Fix aux tests by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1753
Fix for FloorDiv Function Warning by @iprovalo in https://github.com/coqui-ai/TTS/pull/1760
Update download_vctk.sh by @mengting7tw in https://github.com/coqui-ai/TTS/pull/1739
Update decoder.py by @p0p4k in https://github.com/coqui-ai/TTS/pull/1792
Update requirements.txt for python 3.10 support by @p0p4k in https://github.com/coqui-ai/TTS/pull/1791
Update README.md by @yuripourre in https://github.com/coqui-ai/TTS/pull/1776
Fix & update WaveRNN vocoder model by @vanIvan in https://github.com/coqui-ai/TTS/pull/1749
Update requirements.txt; inflect==5.6 by @p0p4k in https://github.com/coqui-ai/TTS/pull/1809
Update README.md; download progress bar in CLI. by @p0p4k in https://github.com/coqui-ai/TTS/pull/1797
Update wavenet.py by @p0p4k in https://github.com/coqui-ai/TTS/pull/1796
Adjust default to be able to process longer sentences by @lkiesow in https://github.com/coqui-ai/TTS/pull/1835
Fix language flags generated by espeak-ng phonemizer by @Lokhozt in https://github.com/coqui-ai/TTS/pull/1801
fix getrandomembeddings --> getrandomembedding by @manmay-nakhashi in https://github.com/coqui-ai/TTS/pull/1726
Introduce numpy and torch transforms by @erogol in https://github.com/coqui-ai/TTS/pull/1705
Implement bucketed weighted sampling for VITS by @erogol in https://github.com/coqui-ai/TTS/pull/1871
capacitron_layers multi speaker bug fix by @manmay-nakhashi in https://github.com/coqui-ai/TTS/pull/1664
updates to dataset analysis notebooks by @jreus in https://github.com/coqui-ai/TTS/pull/1853
Fix BCE loss issue by @erogol in https://github.com/coqui-ai/TTS/pull/1872
Remove deprecated files by @erogol in https://github.com/coqui-ai/TTS/pull/1873
Handle when no batch sampler by @erogol in https://github.com/coqui-ai/TTS/pull/1882
Fix tune wavegrad by @geth-network in https://github.com/coqui-ai/TTS/pull/1844
Add new DE Thorsten models by @erogol in https://github.com/coqui-ai/TTS/pull/1898

New Contributors

@code-review-doctor made their first contribution in https://github.com/coqui-ai/TTS/pull/1532
@taras-sereda made their first contribution in https://github.com/coqui-ai/TTS/pull/1567
@ribeiromiranda made their first contribution in https://github.com/coqui-ai/TTS/pull/1587
@s3781009 made their first contribution in https://github.com/coqui-ai/TTS/pull/1599
@Aya-AlJafari made their first contribution in https://github.com/coqui-ai/TTS/pull/1584
@klotlabs made their first contribution in https://github.com/coqui-ai/TTS/pull/1620
@p0p4k made their first contribution in https://github.com/coqui-ai/TTS/pull/1623
@manmay-nakhashi made their first contribution in https://github.com/coqui-ai/TTS/pull/1641
@camillem made their first contribution in https://github.com/coqui-ai/TTS/pull/1469
@iprovalo made their first contribution in https://github.com/coqui-ai/TTS/pull/1760
@mengting7tw made their first contribution in https://github.com/coqui-ai/TTS/pull/1739
@yuripourre made their first contribution in https://github.com/coqui-ai/TTS/pull/1776
@vanIvan made their first contribution in https://github.com/coqui-ai/TTS/pull/1749
@lkiesow made their first contribution in https://github.com/coqui-ai/TTS/pull/1835
@Lokhozt made their first contribution in https://github.com/coqui-ai/TTS/pull/1801
@jreus made their first contribution in https://github.com/coqui-ai/TTS/pull/1853
@geth-network made their first contribution in https://github.com/coqui-ai/TTS/pull/1844

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.6.2...v0.8.0

- Python
Published by erogol over 3 years ago

tts - v0.8.0 models

✨New models ✨ from @thorstenMueller
✨New models ✨ from @NeonGeckoCom

- Python
Published by erogol over 3 years ago

tts - v0.7.1 models

Add capacitron V2 model to TTS zoo. It's more stable and just as expressive!

- Python
Published by WeberJulian over 3 years ago

tts - v0.7.1

What's Changed

v0.7.1 by @erogol in https://github.com/coqui-ai/TTS/pull/1676

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.7.0...v0.7.1

- Python
Published by erogol over 3 years ago

tts - v0.7.0

What's Changed

Trick to Upsampling to High sampling rates using VITS model by @Edresson in https://github.com/coqui-ai/TTS/pull/1456
Update Coqpit requirement by @Edresson in https://github.com/coqui-ai/TTS/pull/1539
Missing f prefix on f-strings fix by @code-review-doctor in https://github.com/coqui-ai/TTS/pull/1532
tiny improvement in data_path resolvement by @taras-sereda in https://github.com/coqui-ai/TTS/pull/1567
Fix VITS upsampling asserts by @Edresson in https://github.com/coqui-ai/TTS/pull/1550
Fix the bug in eSpeak wrapper for eSpeak version 1.48.15 by @Edresson in https://github.com/coqui-ai/TTS/pull/1560
🐍 Python 3.10.x support and drop Python 3.6 support by @erogol in https://github.com/coqui-ai/TTS/pull/1565
Update CI tests by @erogol in https://github.com/coqui-ai/TTS/pull/1572
Build and publish CPU only Docker image by @erogol in https://github.com/coqui-ai/TTS/pull/1573
Add an assert for the upsampling trick by @erogol in https://github.com/coqui-ai/TTS/pull/1538
Add audio length sampler balancer by @Edresson in https://github.com/coqui-ai/TTS/pull/1561
Change the VITS upsampling interpolation trick to linear by @Edresson in https://github.com/coqui-ai/TTS/pull/1564
Capacitron by @a-froghyar in https://github.com/coqui-ai/TTS/pull/977
Fixed usecuda issue in computeembeddings.py by @ribeiromiranda in https://github.com/coqui-ai/TTS/pull/1587
Training recipes for thorsten dataset by @noranraskin in https://github.com/coqui-ai/TTS/pull/1020
fix invalid json by @s3781009 in https://github.com/coqui-ai/TTS/pull/1599
Use fsspec and torch for embedding file IO by @erogol in https://github.com/coqui-ai/TTS/pull/1581
Adding TTS Tutorials by @Aya-AlJafari in https://github.com/coqui-ai/TTS/pull/1584
Internal formatter by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1629
Update trainingamodel.md by @klotlabs in https://github.com/coqui-ai/TTS/pull/1620
Add synpaflex formatter by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1616
added support for model_info in CLI by @p0p4k in https://github.com/coqui-ai/TTS/pull/1623
v0.7.0 by @erogol in https://github.com/coqui-ai/TTS/pull/1537

New Contributors

@code-review-doctor made their first contribution in https://github.com/coqui-ai/TTS/pull/1532
@taras-sereda made their first contribution in https://github.com/coqui-ai/TTS/pull/1567
@ribeiromiranda made their first contribution in https://github.com/coqui-ai/TTS/pull/1587
@s3781009 made their first contribution in https://github.com/coqui-ai/TTS/pull/1599
@Aya-AlJafari made their first contribution in https://github.com/coqui-ai/TTS/pull/1584
@klotlabs made their first contribution in https://github.com/coqui-ai/TTS/pull/1620
@p0p4k made their first contribution in https://github.com/coqui-ai/TTS/pull/1623

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.6.2...v0.7.0

- Python
Published by erogol over 3 years ago

tts - Speaker Encoder Model

Speaker encoder model and config file.

- Python
Published by Aya-AlJafari over 3 years ago

tts - v0.7.0 models

English Capacitron-T2 models + corresponding HiFiGAN V2 vocoder. Implemented and trained by 👑@a-froghyar
German VITS model trained on Thorsten Dataset by 👑@thorstenMueller 👑@domcross

- Python
Published by WeberJulian almost 4 years ago

tts - v0.6.2

What's Changed

Fix multilingual recipe by @Edresson in https://github.com/coqui-ai/TTS/pull/1354
Fix recipes as to the recent API changes. by @erogol in https://github.com/coqui-ai/TTS/pull/1367
Add docsqa to docs website by @nomagick in https://github.com/coqui-ai/TTS/pull/1363
REBASED: Add support for the speaker encoder training using torch spectrograms by @Edresson in https://github.com/coqui-ai/TTS/pull/1348
Add alphas to control language and speaker balancer by @Edresson in https://github.com/coqui-ai/TTS/pull/1216
Add Voice conversion inference support by @Edresson in https://github.com/coqui-ai/TTS/pull/1337
Update issue template by @erogol in https://github.com/coqui-ai/TTS/pull/1370
Open bible dataset formatter by @Edresson in https://github.com/coqui-ai/TTS/pull/1365
REBASED: Transform Speaker Encoder in a Generic Encoder and Implement Emotion Encoder training support by @Edresson in https://github.com/coqui-ai/TTS/pull/1349
Fix typo workflow text by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1403
Add CITATION.cff by @erogol in https://github.com/coqui-ai/TTS/pull/1404
Fix default phonemizer for ja and zh by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1399
Make Style by @erogol in https://github.com/coqui-ai/TTS/pull/1405
Fix #1380 by @erogol in https://github.com/coqui-ai/TTS/pull/1409
Hinge Gruut version to 2.2.3 by @erogol in https://github.com/coqui-ai/TTS/pull/1419
Update CheckSpectrograms notebook by @erogol in https://github.com/coqui-ai/TTS/pull/1418
Fix #1423 by @Edresson in https://github.com/coqui-ai/TTS/pull/1424
Update model file extension by @erogol in https://github.com/coqui-ai/TTS/pull/1422
Fix model manager by @erogol in https://github.com/coqui-ai/TTS/pull/1436
Add formatting tests by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1437
Update base model wrt 👟 by @erogol in https://github.com/coqui-ai/TTS/pull/1406
Replace webrtcvad by silero-vad by @Edresson in https://github.com/coqui-ai/TTS/pull/1431
Bug fix in freeze encoder by @Edresson in https://github.com/coqui-ai/TTS/pull/1391
Enforce phonemizer definition for synthesis by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1441
Fix G2P backend of the released models by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1461
Add EmbeddingManager and BaseIDManager by @Edresson in https://github.com/coqui-ai/TTS/pull/1374
Update requirements coqui_trainer -> trainer by @erogol in https://github.com/coqui-ai/TTS/pull/1478
Update CONTRIBUTING.md, fix header by @Jackiexiao in https://github.com/coqui-ai/TTS/pull/1463
Add African models by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1511
Print Model's license when downloading by @erogol in https://github.com/coqui-ai/TTS/pull/1512
Improve docsQA default questions by @nomagick in https://github.com/coqui-ai/TTS/pull/1411
patch print license by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1514
v0.6.2 by @erogol in https://github.com/coqui-ai/TTS/pull/1353

New Contributors

@nomagick made their first contribution in https://github.com/coqui-ai/TTS/pull/1363
@Jackiexiao made their first contribution in https://github.com/coqui-ai/TTS/pull/1463

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.6.1...v0.6.2

- Python
Published by erogol almost 4 years ago

tts - v0.6.2 models

This release add 6 new VITS models for languages of the openbible dataset.

ewe
hausa
lingala
yoruba
asante-twi
akuapem-twi

Original work (audio and text) by Biblica available for free at www.biblica.com and open.bible.

- Python
Published by WeberJulian almost 4 years ago

tts - v0.6.1 models

What's Changed

Renamed all checkpoints from model_file.pth.tar to model_file.pth
Tested and fixed for all tts models the "phonemizer" backend key in config

For best performance, you should use the commit version attached to each model

- Python
Published by WeberJulian almost 4 years ago

tts - v0.6.1

- Python
Published by erogol almost 4 years ago

tts - v0.6.0

What's Changed

Tokenizer API

Tokenizer API is defined by the TTSTokenizer class. It is intended to provide all the text processing functionalities to a tts model. New tokenizers can also be added by subclassing the TTSTokenizer class.

Phonemizer API

Phonemizer API is defined by the BasePhonemizer class and implemented by the ESpeak and Gruut wrappers, ZHCH, JPJA phonemizers. New phonemizers can be added by implementing the BasePhonemizer class.

BaseCharacters

BaseCharacters class provides an API to define the model vocabulary and provide the dictionary to map characters to token IDs and back. There are two pre-defined classes inheriting from BaseCharacters. IPAPhonemes and Graphemes that respectively define the IPA phoneme character set for models using phonemes and grapheme set for models using raw characters.

Punctuations class

Punctuations class to strip out punctuations and restore them when needed.

Language specific text normalization routines under `TTS.tts.utils.text`

Under TTS.tts.utils.text there are folders for each language to accommodate the text normalization routines that are designed for the language.

👟Trainer

We separate the trainer as a new repo 👟Trainer. It is a general-purpose model trainer for Pytorch with certain design choices in mind.

Support for different experiment tracking dashboards like ClearML, Tensorboard, MLFlow, and W&Bs.
Flexible to train any kind of DL model.
Simple code base and easily expandable.
Easy to debug.

It is a very early-stage and monolithic library currently. Feel free to share your ✨feedback✨ and ✨contribute✨.

VITS implementation update

With this version of VITS model, we get rid of some of the issues that affect the model performance. It also illustrates well how you could adapt any open-source model implementation to 🐸TTS and 👟Trainer without even knowing the rest for 🐸TTS library.

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.5.0...v0.6.0

New Models

GlowTTS + HifiGAN Turkish by 👑Fatih Akademi

console $ tts --model_name tts_models/tr/common-voice/glow-tts --text "Bu bizim için oluşturulmuş bir örnek sevgili dostum."
VITS and GlowTTS Italian by 👑@nicolalandro using MAI Italian male and female subsets.

Female VITS model console $ tts --model_name tts_models/it/mai_female/vits --text "Questo è un esempio per noi, mio <200b><200b>caro amico."

Male VITS model console $ tts --model_name tts_models/it/mai_male/vits --text "Questo è un esempio per noi, mio <200b><200b>caro amico."

- Python
Published by erogol almost 4 years ago

tts - v0.6.0 models

- Python
Published by erogol almost 4 years ago

tts - v0.5.0

What's Changed

Fix some setup papercuts by @reuben in https://github.com/coqui-ai/TTS/pull/1022
Add additional datasets by @loganhart420 in https://github.com/coqui-ai/TTS/pull/1021
Add UK vocoder models by @erogol in https://github.com/coqui-ai/TTS/pull/1031
Add multilingual models support by @erogol in https://github.com/coqui-ai/TTS/pull/1007
Implement YourTTS by @WeberJulian and @Edresson
Fixes before YourTTS merge by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1044
Fix language assignment by @erogol in https://github.com/coqui-ai/TTS/pull/1047
Fix if else statement by @erogol in https://github.com/coqui-ai/TTS/pull/1050
Fix train_tts.py and uncomment code by @WeberJulian in https://github.com/coqui-ai/TTS/pull/1051
v0.5.0 by @erogol in https://github.com/coqui-ai/TTS/pull/1027

New Contributors

@reuben made their first contribution in https://github.com/coqui-ai/TTS/pull/1022
@loganhart420 made their first contribution in https://github.com/coqui-ai/TTS/pull/1021

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.4.2...v0.5.0

- Python
Published by erogol about 4 years ago

tts - v0.5.0_models

Model releases accompanying v0.5.0

- Python
Published by erogol about 4 years ago

tts - v0.4.2

What's Changed

Model zoo tests by @erogol in https://github.com/coqui-ai/TTS/pull/900
v0.4.2 by @erogol in https://github.com/coqui-ai/TTS/pull/901
Optional silence trimming during inference and find_endpoint() fix by @george-roussos in https://github.com/coqui-ai/TTS/pull/898
Update gruut to version 2.0 by @synesthesiam in https://github.com/coqui-ai/TTS/pull/882
Documentation corrections for finetuning and data preparation by @gullabi in https://github.com/coqui-ai/TTS/pull/931
server: fix compatibility with ttsmodels/en/ljspeech/fastpitch by @Mic92 in https://github.com/coqui-ai/TTS/pull/893
v0.4.2 by @erogol in https://github.com/coqui-ai/TTS/pull/914

New Contributors

@george-roussos made their first contribution in https://github.com/coqui-ai/TTS/pull/898
@gullabi made their first contribution in https://github.com/coqui-ai/TTS/pull/931

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.4.1...v0.4.2

- Python
Published by erogol about 4 years ago

tts - v0.4.1

What's Changed

v0.4.1 by @erogol in https://github.com/coqui-ai/TTS/pull/891

Full Changelog: https://github.com/coqui-ai/TTS/compare/v0.4.0...v0.4.1

- Python
Published by erogol over 4 years ago

tts - v0.4.0

🐸 v0.4.0

Update multi-speaker training API.
VCTK recipes for all the TTS models.
Documentation for multi-speaker training.
Pre-trained Ukrainian GlowTTS model from 👑 https://github.com/robinhad/ukrainian-tts
Pre-trained FastPitch VCTK model
Dataset downloaders for LJSpeech and VCTK under TTS.utils.downloaders
Documentation reformatting.
Trainer V2 and compact. updates in model implementations.

This update makes the Trainer V2 responsible for only the training of a model. The rest is excluded from the trainer and they need to be done either in the model or before calling the trainer.

Try out new models

Pre-trained FastPitch VCTK model

bash tts --model_name tts_models/en/vctk/fast_pitch --text "This is my sample text to voice." --speaker_idx VCTK_p229

Pre-trained Ukrainian GlowTTS model from 👑 https://github.com/robinhad/ukrainian-tts

bash tts --model_name tts_models/uk/mai/glow-tts --text "Це зразок тексту, щоб спробувати нашу модель."

- Python
Published by erogol over 4 years ago

tts - v0.3.1

Mostly fixes for GlowTTS training.

- Python
Published by erogol over 4 years ago

tts - v0.3.0

🐸 v0.3.0

New `ForwardTTS` implementation.

This version implements a new ForwardTTS interface that can be configured as any feed-forward TTS model that uses a duration predictor at inference time. Currently, we provide 3 pre-configured models and plan to implement one more.

SpeedySpeech
FastSpeech
FastPitch
FastSpeech 2 (TODO)

Through this API, any model can be trained in two ways. Either using pre-computed durations from a pre-trained Tacotron model or using an alignment network to learn durations from the dataset. The alignment network is only used at training and discarded at inference. You can set which mode you want to use by just setting the use_aligner field in the configuration.

This new API will help us to design more efficient inference run-time for all these models using ONNX like run-time optimizers.

Old FastPitch and SpeedySpeech implementations are deprecated for the sake of this new implementation.

Fine-Tuning Documentation

This version introduces documentation for model fine-tunning. You can see it under https://tts.readthedocs.io/ when this is merged.

New Model Releases

English Speedy Speech model on LJSpeech

Try out: bash tts --text "This is a sample text for my model to speak." --model_name tts_models/en/ljspeech/speedy-speech

Fine-tuned UnivNet Vocoder

Try out: bash tts --text "This is how it is." --model_name tts_models/en/ljspeech/tacotron2-DDC_ph

- Python
Published by erogol over 4 years ago

tts - v0.2.2

🐸 v0.2.2

FastPitch model with an Aligner Network is implemented with other changes accompanying it.

Alignment Network: https://arxiv.org/abs/2108.10447
Fast Pitch Model: https://arxiv.org/abs/2006.06873

Thanks to 👑 @kaiidams for his Japanese g2p update.

Try FastPitch model: bash tts --model_name tts_models/en/ljspeech/fast_pitch --text "This is my sample text to voice."

- Python
Published by erogol over 4 years ago

tts - v0.2.1

🐸 v0.2.1

🐞Bug Fixes

Fix distributed training and solve compact issues with the Trainer API.
Fix bugs in the VITS model implementation that caused training instabilities.
Fix some Abstract Class usage issues in WaveRNN and WaveGrad models.

💾 Code updates

Use a single gradient scaler for all the optimizers in TrainerAPI. Previously, we used one scaler per optimizer.

🏃‍♀️Operational Updates

Update to Pylint 2.10.2

Thanks to 👑 @fijipants for his fixes 🛠️ Thanks to 👑 @agrinh for his flag and discussion in DDP issues

- Python
Published by erogol over 4 years ago

tts - v0.2.0

🐸 v0.2.0

🐞Bug Fixes

Fix phoneme pre-compute issue.
Fix multi-speaker setup in Tacotron models.
Fix small issues in the Trainer regarding multi-optimizer training.

💾 Code updates

W&B integration for model logging and experiment tracking, (👑 @AyushExel) Code uses the Tensorboard by default. For W&B, you need to set log_dashboard option in the config and define project_name and wandb_entity.
Use ffsspec for model saving/loading (👑 @agrinh)
Allow models to define their own symbol list with in-class make_symbols()
Allow choosing after epoch or after step LR scheduler update with scheduler_after_epoch.
Make converting spectrogram from amplitude to DB optional with do_amp_to_db_linear and do_amp_to_db_linear options.

🗒️ Docs updates

Add GlowTTS and VITS docs.

🤖 Model implementations

VITS implementation with pre-trained models (https://arxiv.org/abs/2106.06103)

🚀 Model releases

vocodermodels--ja--kokoro--hifiganv1 (👑 @kaiidams)

HiFiGAN model trained on Kokoro dataset to complement the existing Japanese model.

Try it out:

bash tts --model_name tts_models/ja/kokoro/tacotron2-DDC --text "こんにちは、今日はいい天気ですか？"
ttsmodels--en--ljspeech--tacotronDDCph

TacotronDDC with phonemes trained on LJSpeech. It is to fix the pronunciation errors caused by the raw text in the released TacotronDDC model.

Try it out:

bash tts --model_name tts_models/en/ljspeech/tacotronDDC_ph --text "hello, how are you today?"
tts_models--en--ljspeech--vits

VITS model trained on LJSpeech.

Try it out:

bash tts --model_name tts_models/en/ljspeech/vits --text "hello, how are you today?"
tts_models--en--vctk--vits

VITS model trained on VCTK with multi-speaker support.

Try it out:

bash tts-server --model_name tts_models/en/vctk/vits
vocoder_models--en--ljspeech--univnet

UnivNet model trained on LJSpeech to complement the TacotronDDC model above.

Try it out:

bash tts --model_name tts_models/en/ljspeech/tacotronDDC_ph --text "hello, how are you today?"

- Python
Published by erogol over 4 years ago

tts - v0.1.3

🐸 v0.1.3

🐞Bug Fixes

Fix Tacotron stopnet training

Models trained after v0.1 had the problem that the stopnet was not trained. It caused models not to generate audio at evaluation and inference time.
Fix test_run at training. (👑 @WeberJulian)

In training :frog: TTS would skip the test_run and not generate test audio samples. Now it is fixed :).
Fix server.py for multi-speaker models.

💾 Code updates

Refactoring in compute_embeddings.py for efficiency and compatibility with the latest speaker encoder. (👑 @Edresson)

🚀 Model releases

New Fullband-MelGAN model for Thorsten German dataset. (👑 @thorstenMueller)

Try it:

python tts --model_name tts_models/de/thorsten/tacotron2-DCA --text "Was geschehen ist geschehen, es ist geschichte."

- Python
Published by erogol over 4 years ago

tts - v0.1.2

- Python
Published by erogol over 4 years ago

tts - v0.1.1

Fix #607 and #608

- Python
Published by erogol over 4 years ago

tts - v0.1.0

🐸 v0.1.0

In a nutshell, there are a ton of updates in this release. I don't know if we can cover them all here but let's try.

After this release, 🐸 TTS stands on the following architecture.

Trainer API for training.
Synthesizer API for inference.
ModelManager API for managing 🐸TTS model zoo.
SpeakerManager API for managing speakers in a multi-speaker setting.
(TBI) Exporter API for exporting models to ONNX, TorchScript, etc.
(TBI) Data Processing API for making a dataset ready for training.
Model API for implementing models, compatible with all the other components above.

Updates

💾 Code updates

Brand new Trainer API

We unified all the training code in a lightweight but feature complete Trainer API. From now on all the 🐸TTS models will use this new API for training.

It provides mixed precision (with Nvidia's APEX of torch.amp) and multi-gpu training for all the models.
Brand new Model API

Abstract BaseModel and its BaseTTS, BaseVocoder child classes are used as the basis of the 🐸TTS models now. Any model that implements one of these classes, works seamlessly with the Trainer and Synthesizer.
Brand new 🐸TTS recipes.

We decided to merge the recipes to the main project. Now we host recipes for the LJspeech dataset, covering all the implemented models. So you can pick the model you want, change the parameters, and train your own model easily.

Thanks to the new Trainer API and 👩‍✈️Coqpit integration, we could implement these recipes with pure python.
Updates SpeakerManager API

TTS.utilsSpeakerManager is now the core unit to manage speakers in a multi-speaker model and interface a SpeakerEncoder model with the tts and vocoder models.
Updated model training mechanics.

You can now use pure Python to define your model and run the training. It is useful to train models on a Jupyter Notebook or the other python environments.

We also keep the old mechanics by using TTS/bin/train_tts.py or `TTS/bin/train_vocoder.py. You just need to change the previous training script name with one of these two based on your model.

bash python TTS/bin/train_tacotron.py --config_path config.json

becomes

bash python TTS/bin/train_tts.py --config_path config.json
Use 👩‍✈️Coqpit for managing model class arguments.

Now all the model arguments are defined in a coqpit class and imported by the model config.
gruut based character to phoneme conversion. (👑 @synesthesiam)

As a drop-in replacement for the previous solution that is compatible with the released models. So now all these models are functional again without version nitpicking.
Set test_sentences in the config rather than providing a txt file.
Set the maximum number of decoder steps of Tacotron1-2 models in the config.

🏃‍♀️ Operational Updates

FINALLY DOCUMENTATION!! https://tts.readthedocs.io
Enable support for Python 3.9
Changes for PyTorch 1.9.0

🏅 Model implementations

Univnet GAN Vocoder: https://arxiv.org/pdf/2106.07889.pdf (👑 @rishikksh20)

🚀 Model releases

We solved the compat issues and re-release some of the models. You can see them in the released binaries section.

You don't need to change anything. If you use v0.1.0, by default, it uses these new models.

- Python
Published by erogol over 4 years ago

tts - v0.0.15.1

Fix manifest file to include VERSION for pypi distribution.

- Python
Published by erogol over 4 years ago

tts - v0.0.15

🐸 v0.0.15

🐞Bug Fixes

[x] Fix tb_logger init for rank > 0 processes in distributed training.

💾 Code updates

[x] Refactoring and optimization in the speaker encoder module. (:crown: @Edresson )
[x] Replacing unidecode with anyascii
[x] Japanese text to phoneme conversion. (:crown: @kaiidams)
[x] Japanese tts recipe to train Tacotron2-DDC on Kokoro dataset (:crown: @kaiidams)

:walking_woman: Operational Updates

[x] Start using pylint == 2.8.3
[x] Reorg tests files.
[x] Upload to pypi automatically on release.
[x] Move VERSION file under TTS folder.

🏅 Model implementations

[x] New Speaker Encoder implementation based on https://arxiv.org/abs/2009.14153 (:crown: @Edresson )

🚀 New Pre-Trained Model Releases

[x] Japanese Tacotron model (:crown: @kaiidams)

:bulb: All the models below are available by tts or tts-server endpoints on CLI as explained here.

- Python
Published by erogol over 4 years ago

tts - v0.0.14

:frog: v0.0.14

🐞Bug Fixes

[x] Remove breaking line from Tacotron models. (👑 @a-froghyra)

💾 Code updates

[x] BREAKING: Coqpit integration for config management and the first 🐸TTS recipe, for LJSpeech Check #476.

Every model now tied to a Python class that defines the configuration scheme. It provides a better interface and lets the user know better what are the default values, expected value types, and mandatory fields.

Specific model configs are defined under TTS/tts/configs and TTS/vocoder/configs. TTS/config/shared_configs.py hosts configs that are shared by all the :frog: TTS models. Configs shared by tts models are hosted under TTS/tts/configs/shared_configs.py and shared by vocoder models are under TTS/vocoder/configs/shared_config.py.

For example TacotronConfig follows BaseTrainingConfig -> BaseTTSConfig -> TacotronConfig. - [x] BREAKING: Remove phonemizer support due to License conflict.

This essentially deprecates the support for all the models using phonemes as input. Feel free to suggest in-place options if you are affected by this change.

[x] Start hosting :woman_cook: recipes under :frog: TTS. The first recipe is for Tacotron2-DDC with LJspeech dataset under TTS/recipes/.

Please check here for more details. - [x] Add extract_tts_spectrograms.py that supports GlowTTS and Tacotron1-2. (👑 @Edresson) - [x] Add version.py (👑 @chmodsss)

- Python
Published by erogol almost 5 years ago

tts - v0.0.13

:frog: v0.0.13

🐞Bug Fixes

💾 Code updates

SpeakerManager class for handling multi-speaker model management and interfacing speaker.json file.
Enabling multi-speaker models with tts and tts-server endpoints. (:crown: @kirianguiller )
Allow choosing a different noise scale for GlowTTS at inference.
Glow-TTS updates to import SC-Glow Models.
Fixing windows support (:crown: @WeberJulian )

:walking_woman: Operational Updates

Refactoring :frog: TTS installation and allow selecting different scopes (all, tf, notebooks)for installation depending on the specific needs.

🏅 Model implementations

🚀 New Pre-Trained Model Releases

SC-GlowTTS multi-speaker English model from our work https://arxiv.org/abs/2104.05557 (:crown: @Edresson )
HiFiGAN vocoder finetuned for the above model.
Tacotron DDC Non-Binary English model using Accenture's Sam dataset.
HiFiGAN vocoder trained for the models above.

Released Models

:bulb: All the models below are available by tts or tts-server endpoints on CLI as explained here.

Models with ✨️ below are new with this release.

SC-GlowTTS model is from our latest paper in a collaboration with @Edresson and @mueller91.
The new non-binary TTS model is trained using the SAM dataset from Accenture Labs. Check out their blog post

Update Jun 7 2021: Ruslan (Russian) model has been removed due to the license conflict.

- Python
Published by erogol almost 5 years ago

tts - v0.0.12

:frog: v0.0.12

🐞Bug Fixes

[x] fix #419 (This is a crucial bug fix).
[x] fix #408

💾 Code updates

[x] Enable logging model config.json on Tensorboard. #418
[x] Update code style standards and use a Makefile to ease regular tasks. #423
[x] Enable using Tacotron.prenet.dropout at inference time. This leads to a better quality with some models.
[x] Update default tts model to LJspeech TacotronDDC.
[x] Show the real waveform on Tensorboard in GAN vocoder training.

:walking_woman: Operational Updates

🏅 Model implementations

[x] initial HiFiGAN implementation (:crown: @rishikksh20 @erogol) #422

🚀 New Pre-Trained Model Releases

[ ] ~~Universal HifiGAN model~~(postponed to the next version for :crown: @Edresson's updated model.)
[x] LJSpeech, Tacotron2 Double Decoder Consistency v2 model. Check our blog post to learn more about Double Decoder Consistency.
[x] LJSpeech HifiGAN model.

Released Models

:bulb: All the models below are available by tts end point as explained here.

- Python
Published by erogol almost 5 years ago

tts - v0.0.11

:frog: v0.0.11

🐞Bug Fixes

[x] Fixed #374. (Thx for reporting @a-froghyar )

💾 Code updates

[x] /bin/resample.py to resample wavefiles (:crown: @WeberJulian)
[x] Some updates for Windows compat. (:crown: @GuyPaddock)
[x] Fixing CheckSpectrogram notebook. (:crown: @GuyPaddock)
[x] Fix #392

:walking_woman: Operational Updates

🏅 Model implementations

[x] initial AlignTTS implementation. (https://github.com/coqui-ai/TTS/pull/398)
[ ] initial HiFiGAN implementation (:crown: @rishikksh20) (postponed to the next release)

🚀 New Pre-Trained Model Releases

[x] German - Tacotron2-DCA trained with thorsten_dataset. (:crown: @thorstenMueller )
[x] German - Wavegrad vocoder with thorsten_dataset. (:crown: @thorstenMueller)

Released Models

:bulb: All the models below are available by tts end point as explained here.

- Python
Published by erogol almost 5 years ago

tts - v0.0.10

:frog: v0.0.10

🐞Bug Fixes

[x] Make synthesizer.py saving the output audio with the vocoder sampling rate. It is necessary if there is sampling rates of the tts and the vocoder models are different and interpolation is applied to the tts model output before running the vocoder. Practically, it fixes generated Spanish and French voices by tts or tts-server on the terminal.
[x] Handling utf-8 on Windows. (by @adonispujols)
[x] Fix Loading the last model when --continue_training. It was loading the best_model regardless.

💾 Code updates

[x] Breaking Change: Update default set of characters in symbols.py. This might require you to set your character set in config.json if you like to use this version with your models trained with the previous version.
[x] Chinese backend for text processing (#654 by @kirianguiller)
[x] Enable torch.hub integration for the released models.
[x] First github release.
[x] dep. version fixes. Using numpy > 1.17.5 breaks some tests.
[x] WaveRNN fix (by @gerazov )
[x] Big refactoring for the training scripts to share the init part of the code. (by @gerazov)
[x] Enable ModelManager to download models from Github releases.
[x] Add a test for compute_statistics.py
[x] light-touch updates in tts and tts-server entry points. (thanks @thorstenMueller )
[x] Define default vocoder models for each tts model in .models.json. tts and tts-server entry points use the default vocoder if the user does not specify.
[x] find_unique_chars.py to find all the unique characters in a dataset.
[x] A better way to handling best models through training. (thx @gerazov )
[x] pass used characters to the model config.json at the beginning of the training. This prevents any code update later to affect the trained models.
[x] Migration to Github Actions for CI.
[x] Deprecate wheel based use of tts-server for the sake of the new design.
[x] :frog:

:walking_woman: Operational Updates

[x] Move released models to Github Releases and deprecate GDrive being the first option.

🏅 Model implementations

No updates 😓

🚀 New Pre-Trained Model Releases

[x] English ek1 - Tacotron2 model and WaveGrad vocoder under .models.json. (huge THX!! to @nmstoker)
[x] Russian Ruslan - Tacotron2-DDC model.
[x] Dutch model. (huge THX!! to @r-dh )
[x] Chinese Tacotron2 model. (huge THX!! to @kirianguiller)
[x] English LJSpeech - SpeechSpeech with WaveNet decoder.

Released Models

:bulb: All the models below are available by tts end point as explained here.

- Python
Published by erogol almost 5 years ago

tts - v0.0.9

:frog: TTS v0.0.9 - the first release :tada:

This is the first and v0.0.9 release of :frog:TTS. :frog:TTS is still an evolving project and any upcoming release might be significantly different and not backward compatible.

In this release, we provide the following models.

Notes

Multi-Lang vocoder models are intended for non-English models.
Vocoder models are independently trained from the tts models with possibly different sampling rates. Therefore, the performance is not optimal.
All models are trained with phonemes generated by espeak back-end (not espeak-ng).
This release has been tested under Python 3.6, 3.7, and 3.8. It is strongly suggested to use conda to install the dependencies and set up the environment.

Edit:

(22.03.2021) - Fullband Universal Vocoder is corrected with the right model files. Previously, we released the wrong model with that name.

- Python
Published by erogol almost 5 years ago

Recent Releases of tts

tts - v0.22.0

What's Changed

New Contributors

tts - v0.21.3

What's Changed

No-Code XTTS fine-tuning

tts - v0.21.2

What's Changed

New Contributors

get v2.0.2

get the latest version

generate speech by cloning a voice using default settings

get v2.0.2

generate speech by cloning a voice using default settings

tts - v0.21.1

tts - v0.21.0

What's Changed

New Contributors

tts - v0.20.6

What's Changed

tts - v0.20.5

What's Changed

tts - v0.20.4

What's Changed

tts - v0.20.3

What's Changed

tts - v0.20.2

What's Changed

New Contributors

tts - v0.20.1

What's Changed

tts - v0.20.0

What's Changed

tts - v0.19.1

What's Changed

New Contributors

tts - v0.19.0

What's Changed

tts - v0.18.2

What's Changed

tts - v0.18.1

What's Changed

tts - v0.18.0

What's Changed

XTTS v1.1

Changes

tts - v0.17.10

tts - v0.17.9

What's Changed

New Contributors

tts - v0.17.8

What's Changed

tts - v0.17.7

What's Changed

New Contributors

tts - v0.17.6

What's Changed

New Contributors

tts - v0.17.5

What's Changed

New Contributors

tts - v0.17.4

tts - v0.17.3

tts - v0.17.2

What's Changed

tts - v0.17.1

tts - 👑v0.17.0

What's Changed

New Contributors

What's Changed

New Contributors

tts - v0.16.6

What's Changed

New Contributors

tts - v0.16.5

What's Changed

tts - v0.16.4

What's Changed

New Contributors

It assumes that you have a speaker file in `bark_voices/speaker_n/speaker.wav` or `bark_voices/speaker_n/speaker.npz`

This expects to find a mp3 or wav file like `bark_voices/new_speaker/speaker.wav`

It computes the cloning values and stores in `bark_voices/new_speaker/speaker.npz`

cloning the `ljspeech` voice

TTS with voice conversion to a reference speaker in `target_speaker.wav`

TTS with voice conversion to a reference speaker in `target_speaker.wav`