a425ba599d
feat: allow both Path and strings where possible and add type hints
2024-12-14 16:19:38 +01:00
b545ab8b80
Merge pull request #197 from idiap/api
...
Expand Python API capabilities
2024-12-06 18:02:54 +01:00
e0f621180f
refactor(bin.synthesize): use Python API for CLI
2024-12-06 17:07:54 +01:00
e8d99aaf2b
Merge pull request #184 from idiap/xtts-error
...
fix(xtts): clearer error message when file given to checkpoint_dir
2024-12-06 06:46:48 +01:00
fe14ca6b68
refactor(xtts): remove duplicate xtts audio config
2024-12-05 15:46:28 +01:00
5f8ad4c64b
test(openvoice): add sanity check
2024-12-02 23:26:28 +01:00
9ef2c7ed62
test(freevc): fix output length check
2024-12-02 23:26:28 +01:00
546f43cb25
refactor: only use keyword args in Synthesizer
2024-12-02 23:26:27 +01:00
d488441b75
test(freevc): remove unused code
2024-12-02 23:26:27 +01:00
63625e79af
refactor: import get_last_checkpoint from trainer.io
2024-11-29 13:59:43 +01:00
7330ad8854
refactor: move duplicate alignment functions into helpers
2024-11-24 19:57:14 +01:00
8bf288eeab
test: move test_helpers.py to fast unit tests
2024-11-24 19:57:14 +01:00
76df6421de
refactor: move more audio processing into torch_transforms
2024-11-24 19:57:14 +01:00
7cdfde226b
refactor: move amp_to_db/db_to_amp into torch_transforms
2024-11-23 01:04:17 +01:00
36611a7192
feat: normalize unicode characters in text cleaners ( #85 )
...
* Add normalizer type C to text cleaners
* Linter recommendations
* Add unicode normalize to every cleaner
* Format test_text_cleaners.py
2024-10-02 17:01:19 +02:00
0fb26f97df
refactor: use get_user_data_dir from trainer
2024-06-29 15:07:10 +02:00
c5241d71ab
chore: address pytorch deprecations
...
torch.range(a, b) == torch.arange(a, b+1)
meshgrid indexing: https://github.com/pytorch/pytorch/issues/50276
checkpoint use_reentrant:
https://dev-discuss.pytorch.org/t/bc-breaking-update-to-torch-utils-checkpoint-not-passing-in-use-reentrant-flag-will-raise-an-error/1745
optimizer.step() before scheduler.step():
https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
2024-06-26 11:38:25 +02:00
857cd55ce5
test(helpers): fix test_rand_segment, test_generate_path
2024-06-26 10:16:46 +02:00
c9f7197862
test(helpers): add test_ prefix so tests actually run
2024-06-25 23:03:40 +02:00
e5c208d254
feat(cleaners): add multilingual phoneme cleaner
...
This doesn't convert numbers into English words.
2024-06-14 15:06:03 +02:00
77722cb0dd
fix(bin.synthesize): correctly handle boolean arguments
...
Previously, e.g. `--use_cuda false` would actually set use_cuda=True:
https://github.com/coqui-ai/TTS/discussions/3762
2024-05-31 08:39:32 +02:00
07cbcf825c
fix(espeak_wrapper): read phonemize() input from file
...
Avoids utf8 encoding issues on Windows when passing the text directly.
Fixes https://github.com/coqui-ai/TTS/discussions/3761
2024-05-29 10:10:05 +02:00
ec50006855
style: run pre-commit
...
Automatic changes from: pre-commit run --all-files
2024-05-08 12:17:47 +02:00
98e21d0f02
test(losses): change assertEqual to assertAlmostEqual
...
Failed in CI with:
AssertionError: 1.401298464324817e-45 != 0.0
2024-05-01 14:28:55 +02:00
b711e19cb6
refactor: remove verbose arguments
...
Can be handled by adjusting logging levels instead.
2024-04-03 15:19:45 +02:00
a7753708fb
refactor: remove duplicate methods available in Trainer
2024-03-12 15:06:42 +01:00
dca564a705
test(vocoder): disable wavegrad training test in CI
2024-03-08 17:27:23 +01:00
efdafd5a7f
style: run black
2024-03-07 11:46:51 +01:00
24298da5fc
Merge pull request #1 from eginhard/lint-overhaul
...
Lint overhaul (pylint to ruff)
2024-03-06 16:10:26 +01:00
1961687a18
build: update to ruff 0.3.0
2024-03-06 13:40:56 +01:00
5dcc16d193
Bug fix in MP3 and FLAC compute length on TTSDataset ( #3092 )
...
* Bug Fix on XTTS load
* Bug fix in MP3 length on TTSDataset
* Update TTS/tts/datasets/dataset.py
Co-authored-by: Aarni Koskela <akx@iki.fi>
* Uses mutagen for all audio formats
* Add dataloader test wit hall supported audio formats
* Use mutagen.File
* Update
* Fix aux unit tests
* Bug fixe on unit tests
---------
Co-authored-by: Aarni Koskela <akx@iki.fi>
2023-12-27 13:23:43 -03:00
64bb41f4fa
Ruff autofix C41
2023-12-13 14:56:41 +02:00
90991e89b4
Ruff autofix unused imports and import order
2023-12-13 14:56:41 +02:00
72ac2bfa09
Get rid of some star imports
2023-12-13 14:56:41 +02:00
8999780aff
Update test_models.py
2023-12-12 13:30:21 +01:00
605a857add
Remove tortoise
2023-12-11 23:35:07 +01:00
8c20a599d8
Remove coqui studio integration from TTS
2023-12-11 22:11:46 +01:00
39321d02be
fix: correctly strip/restore initial punctuation ( #3336 )
...
* refactor(punctuation): remove orphan code for handling lone punctuation
The case of lone punctuation is already handled at the top of restore(). The
removed if statement would never be called and would in fact raise an
AttributeError because the _punc_index named tuple doesn't have the attribute
`mark`.
* refactor(punctuation): remove unused argument
* fix(punctuation): correctly handle initial punctuation
Stripping and restoring initial punctuation didn't work correctly because the
string-splitting caused an additional empty string to be inserted in the text
list (because `".A".split(".")` => `["", "A"]`). Now, an initial empty string is
skipped and relevant test cases are added.
Fixes #3333
2023-11-30 13:03:16 +01:00
b47d9c6e36
Merge pull request #3243 from idiap/checkpoints
...
Remove duplicate/unused code
2023-11-22 23:52:06 +01:00
44880f09ed
Make style
2023-11-17 13:43:34 +01:00
0fb0d67de7
refactor: use save_checkpoint()/save_best_model() from Trainer
2023-11-17 01:18:23 +01:00
3c2d5a9e03
Remove duplicate AudioProcessor code and fix ExtractTTSpectrogram.ipynb ( #3230 )
...
* chore: remove unused argument
* refactor(audio.processor): remove duplicate stft+griffin_lim
* chore(audio.processor): remove unused compute_stft_paddings
Same function available in numpy_transforms
* refactor(audio.processor): remove duplicate db_to_amp
* refactor(audio.processor): remove duplicate amp_to_db
* refactor(audio.processor): remove duplicate linear_to_mel
* refactor(audio.processor): remove duplicate mel_to_linear
* refactor(audio.processor): remove duplicate build_mel_basis
* refactor(audio.processor): remove duplicate stft_parameters
* refactor(audio.processor): use pre-/deemphasis from numpy_transforms
* refactor(audio.processor): use rms_volume_norm from numpy_transforms
* chore(audio.processor): remove duplicate assert
Already checked in numpy_transforms.compute_f0
* refactor(audio.processor): use find_endpoint from numpy_transforms
* refactor(audio.processor): use trim_silence from numpy_transforms
* refactor(audio.processor): use volume_norm from numpy_transforms
* refactor(audio.processor): use load_wav from numpy_transforms
* fix(bin.extract_tts_spectrograms): set quantization bits
* fix(ExtractTTSpectrogram.ipynb): adapt to current TTS code
Fixes #2447 , #2574
* refactor(audio.processor): remove duplicate quantization methods
2023-11-16 10:57:06 +01:00
04901fb2e4
Add speed control for inference ( #3214 )
...
* Add speed control for inference
* Fix XTTS tests
* Add speed control tests
2023-11-14 16:07:17 +01:00
b2682d39c5
Make style
2023-11-13 13:01:01 +01:00
58cb0d8dd0
Remove v1 doc and tests ( #3172 )
...
* remove v1 in inference.md
* remove v1 in README.md
* Update test_models.py
2023-11-08 14:51:42 +01:00
b146de4ce8
Bug fix on XTTS v2.0 Trainer
2023-11-06 20:26:01 +01:00
f444f296f2
Add multiples references on xtts inference tests
2023-11-06 20:25:06 +01:00
1b6f8d0e46
Update unit tests and recipes
2023-11-06 20:25:06 +01:00
f0cb19ecca
Drop diffusion from XTTS ( #3150 )
...
* Drop diffusion for XTTS
* Make style
* Drop diffusion deps in code
* Restore thrashed
2023-11-06 20:15:49 +01:00
e45227d9ff
XTTS v2.0 ( #3137 )
...
* Implement most similar ref training approach
* Use non-enhanced hifigan for test samples
* Add Perceiver
* Update GPT Trainer for perceiver support
* Update XTTS docs
* Bug fix masking with XTTS perceiver
* Bug fix on gpt forward
* Bug Fix on XTTS v2.0 training
* Add XTTS v2.0 unit tests
* Add XTTS v2.0 inference unit tests
* Bug Fix on diffusion inference
* Add XTTS v2.0 training recipe
* Placeholder model entry
* Add cloning params to config
* Make prompt embedding configurable
* Make cloning configurable
* Cheap fix for a cheaper fix
* Prevent resampling
* Update model entry
* Update docs
* Update requirements
* Code linting
* Add xtts v2 to sep tests
* Bug fix on XTTS get_gpt_cond_latents
* Bug fix on rebase
* Make style
* Bug fix in Japenese tokenizer
* Add num2words to deps
* Remove unused kwarg and added num_beams=1 as default
---------
Co-authored-by: Eren G??lge <egolge@coqui.ai>
2023-11-06 14:58:18 +01:00
Enno Hermann
Enno Hermann
Shavit
Edresson Casanova
Aarni Koskela
Eren Gölge
WeberJulian
Eren G??lge