Enno Hermann
5f8ad4c64b
test(openvoice): add sanity check
2024-12-02 23:26:28 +01:00
Enno Hermann
9ef2c7ed62
test(freevc): fix output length check
2024-12-02 23:26:28 +01:00
Enno Hermann
546f43cb25
refactor: only use keyword args in Synthesizer
2024-12-02 23:26:27 +01:00
Enno Hermann
6927e0bb89
fix(api): clearer error message when model doesn't support VC
2024-12-02 23:26:27 +01:00
Enno Hermann
d488441b75
test(freevc): remove unused code
2024-12-02 23:26:27 +01:00
Enno Hermann
fce3137e0d
feat: add openvoice vc model
2024-12-02 23:26:27 +01:00
Enno Hermann
1a21853b90
ci: validate .models.json file
2024-12-02 22:34:56 +01:00
Enno Hermann
ca02d0352b
feat(openvoice): add to .models.json
2024-12-02 22:34:56 +01:00
Enno Hermann
95998374bf
feat(openvoice): add config classes
2024-12-02 22:34:56 +01:00
Enno Hermann
b97d5378a5
refactor(openvoice): remove duplicate and unused code
2024-12-02 22:34:56 +01:00
Enno Hermann
4124b9d663
feat(vits): add tau parameter to posterior encoder
2024-12-02 22:34:56 +01:00
akulkarni
6de98ff480
feat(openvoice): initial integration
2024-12-02 22:34:56 +01:00
Enno Hermann
98a372bca2
Merge pull request #172 from idiap/deduplicate
...
Remove unused code
2024-12-02 16:25:31 +01:00
Enno Hermann
63625e79af
refactor: import get_last_checkpoint from trainer.io
2024-11-29 13:59:43 +01:00
Enno Hermann
170d3dae92
refactor: remove duplicate to_camel
2024-11-24 19:57:14 +01:00
Enno Hermann
7330ad8854
refactor: move duplicate alignment functions into helpers
2024-11-24 19:57:14 +01:00
Enno Hermann
8bf288eeab
test: move test_helpers.py to fast unit tests
2024-11-24 19:57:14 +01:00
Enno Hermann
76df6421de
refactor: move more audio processing into torch_transforms
2024-11-24 19:57:14 +01:00
Enno Hermann
2c82477a78
ci: merge integration tests back into unit tests
2024-11-24 19:57:14 +01:00
Enno Hermann
b1ac884e07
refactor: move shared function into dataset.py
2024-11-24 19:57:14 +01:00
Enno Hermann
54f4228a46
refactor(xtts): use existing cleaners
2024-11-24 19:57:14 +01:00
Enno Hermann
b45a7a4220
refactor: move exists() and default() into generic_utils
2024-11-24 19:57:14 +01:00
Enno Hermann
fa844e0fb7
refactor(tacotron): remove duplicate function
2024-11-24 19:57:14 +01:00
Enno Hermann
0f69d31f70
refactor(vocoder): remove duplicate function
2024-11-24 19:57:14 +01:00
Enno Hermann
6ecf47312c
refactor(xtts): use tortoise conditioning encoder
2024-11-24 19:57:14 +01:00
Enno Hermann
69a599d403
refactor(freevc): remove duplicate code
2024-11-24 19:57:14 +01:00
Enno Hermann
2e5f68df6a
refactor(wavernn): remove duplicate Stretch2d
...
I checked that the implementations are the same
2024-11-23 01:04:17 +01:00
Enno Hermann
e63962c226
refactor(losses): move shared losses into losses.py
2024-11-23 01:04:17 +01:00
Enno Hermann
6f25c2b904
refactor(delightful_tts): remove unused classes
2024-11-23 01:04:17 +01:00
Enno Hermann
7cdfde226b
refactor: move amp_to_db/db_to_amp into torch_transforms
2024-11-23 01:04:17 +01:00
Enno Hermann
33ac0d6ee1
refactor(xtts): use build_hf_gpt_transformer from tortoise
2024-11-21 15:44:42 +01:00
Enno Hermann
490c973371
refactor(xtts): use position embedding from tortoise
2024-11-21 15:44:42 +01:00
Enno Hermann
5ffc0543b7
refactor(bark): remove custom layer norm
...
Pytorch LayerNorm supports bias=False since version 2.1
2024-11-21 15:44:42 +01:00
Enno Hermann
705551c60c
refactor(tortoise): remove unused do_checkpoint arguments
...
These are assigned but not used for anything.
2024-11-21 15:44:42 +01:00
Enno Hermann
4ba83f42ab
chore(tortoise): remove unused AudioMiniEncoder
...
There's one in tortoise.classifier that's actually used
2024-11-21 15:44:42 +01:00
Enno Hermann
66701e1e51
refactor(xtts): reuse functions/classes from tortoise
2024-11-21 12:51:42 +01:00
Enno Hermann
1f27f994a1
refactor(utils): remove duplicate set_partial_state_dict
2024-11-21 11:53:35 +01:00
Enno Hermann
1b6d3ebd33
refactor(xtts): remove duplicate hifigan generator
2024-11-21 11:53:35 +01:00
Enno Hermann
9035e36b1f
ci: allow testing out trainer/coqpit branches before release ( #168 )
2024-11-20 16:34:58 +01:00
Enno Hermann
312593e119
Merge pull request #166 from idiap/error-messages
...
Automatically convert audio to mono, add more helpful error messages
2024-11-20 11:21:28 +01:00
Enno Hermann
fbbae5ac6a
refactor(audio): remove duplicate rms_volume_norm function
2024-11-18 10:01:52 +01:00
Enno Hermann
8ba3233ec6
refactor(audio): remove duplicate save_wav code
2024-11-18 10:01:50 +01:00
Enno Hermann
5784f6705a
refactor(audio): improve type hints, address lint issues
2024-11-18 10:00:55 +01:00
Enno Hermann
48f5be2ccb
feat(audio): automatically convert audio to mono
2024-11-18 01:11:43 +01:00
Enno Hermann
627bbe4150
fix(xtts): more helpful error message when vocab.json not found
2024-11-17 00:30:32 +01:00
Enno Hermann
e81f8d079c
fix: more helpful error message when formatter is not found
2024-11-17 00:29:49 +01:00
Andy
75d082563e
fix(docker): add Support for building Docker on Mac/arm64 ( #159 )
...
* Add Support for building Docker on arm64
* fixup! Add Support for building Docker on arm64
---------
Co-authored-by: Enno Hermann <enno.hermann@idiap.ch>
2024-11-14 16:06:56 +01:00
Enno Hermann
b5bd9953c7
Merge pull request #149 from idiap/cache-models
...
Show original model URLs
2024-11-11 13:24:56 +01:00
Enno Hermann
d3c3ba3d56
build: set upper limit on transformers
...
More breaking changes affecting the XTTS streaming code
2024-11-10 22:58:37 +01:00
Enno Hermann
5de47e9a14
ci: run integration tests only on lowest and highest python
2024-11-10 22:39:58 +01:00