Edresson Casanova
|
8479a3702c
|
Update GPT Trainer for perceiver support
|
2023-11-06 11:37:08 +01:00 |
Edresson Casanova
|
dff3902ca8
|
Add Perceiver
|
2023-11-06 11:37:08 +01:00 |
Edresson Casanova
|
1fb6c203ab
|
Use non-enhanced hifigan for test samples
|
2023-11-06 11:37:08 +01:00 |
Edresson Casanova
|
077a849b3b
|
Implement most similar ref training approach
|
2023-11-06 11:37:08 +01:00 |
Aarni Koskela
|
38f6f8f0bb
|
Run `make style` & re-enable it in CI (#3127)
|
2023-11-06 11:36:37 +01:00 |
WeberJulian
|
1c98821359
|
Remove unused load_audio function
|
2023-10-27 22:27:18 +02:00 |
WeberJulian
|
d4e08c8d6c
|
Add features to get_conditioning_latents
|
2023-10-26 14:57:33 +02:00 |
WeberJulian
|
c1133724a1
|
Move lang token add to tokenizer
|
2023-10-26 14:52:13 +02:00 |
WeberJulian
|
6fa46d197d
|
Fix get_conditioning_latents when using only ne
|
2023-10-26 14:51:35 +02:00 |
Edresson Casanova
|
01839af926
|
Bug fix on XTTS masking training
|
2023-10-24 18:30:14 -03:00 |
Edresson Casanova
|
0f96abb5ec
|
Add FT inference example on XTTS docs
|
2023-10-23 13:23:30 -03:00 |
Edresson Casanova
|
37b7945474
|
Update XTTS train not implemented error to point to the XTTS docs
|
2023-10-23 11:39:17 -03:00 |
Edresson Casanova
|
ec7f54768a
|
Rebase bug fix and update recipe
|
2023-10-21 17:37:51 -03:00 |
Edresson Casanova
|
affaf11148
|
Add XTTS training unit test
|
2023-10-21 13:41:12 -03:00 |
Edresson Casanova
|
1f92741d6a
|
Fix issue #2971
|
2023-10-21 13:37:21 -03:00 |
Edresson Casanova
|
5f98dbeec9
|
Update Ljspeech XTTS recipe
|
2023-10-21 13:37:21 -03:00 |
Edresson Casanova
|
9e3598c3b7
|
Bug Fix on inference using XTTS trainer checkpoint
|
2023-10-21 13:37:21 -03:00 |
Edresson Casanova
|
c4ceaabe2c
|
Add test sentences during the training
|
2023-10-21 13:33:56 -03:00 |
Edresson Casanova
|
2f868dd5c2
|
Bug fix on reproducible evaluation
|
2023-10-21 13:33:56 -03:00 |
Edresson Casanova
|
bafab049c2
|
Add prompting masking
|
2023-10-21 13:33:56 -03:00 |
Edresson Casanova
|
47d613df3a
|
Add reproducible evaluation
|
2023-10-21 13:33:56 -03:00 |
Edresson Casanova
|
40a4e631ea
|
Update mel spectrogram for the style encoder
|
2023-10-21 13:33:56 -03:00 |
Edresson Casanova
|
a32961bcb4
|
Add XTTS base training code
|
2023-10-21 13:33:56 -03:00 |
Julian Weber
|
dad6a7b0b6
|
Preserve [ja] token of the text processing
|
2023-10-21 11:26:03 +02:00 |
Julian Weber
|
c7a16042e3
|
Remove global cutlet import
|
2023-10-21 11:18:58 +02:00 |
Edresson Casanova
|
59576fc0ec
|
Bug fix on XTTS v1.1 inference (#3093)
* Bug fix on XTTS v1.1 inference
* Update .models.json
---------
Co-authored-by: Julian Weber <julian.weber@hotmail.fr>
|
2023-10-20 17:29:43 -03:00 |
Julian Weber
|
cf97116185
|
XTTS v1.1 (#3089)
* Add support for ne_hifigan
* Update model.json
* Update hash
* Fix model loading
* Enhance text_normalization
* Add xtts to zoo test exception
* Add model hash check
* Add get_number_tokens
|
2023-10-20 16:02:08 +02:00 |
Aya Jafari
|
ffddf10458
|
unit test fix
|
2023-10-13 10:56:47 -03:00 |
Aya Jafari
|
6eaecab0ca
|
fixed bugs in fastpitch tts synthesis
|
2023-10-10 23:02:31 -03:00 |
Julian Weber
|
e5e0cbffc9
|
Streaming inference for XTTS 🚀 (#3035)
|
2023-10-06 18:34:06 +02:00 |
Edresson Casanova
|
4c3c11c958
|
Tortoise inference fix and fix zoo unit tests (#3010)
|
2023-09-29 13:40:57 +02:00 |
Aarni Koskela
|
33a7c722f6
|
Merge duplicate on_train_step_start functions in delightful_tts
|
2023-09-27 01:10:44 +03:00 |
Aarni Koskela
|
861c68b0b8
|
Rename misnamed setter
|
2023-09-27 01:09:59 +03:00 |
Aarni Koskela
|
09e14e68db
|
Remove duplicate get_named_beta_schedules
|
2023-09-27 01:09:59 +03:00 |
Aarni Koskela
|
59f85a7122
|
Remove duplicate code from xtts.tokenizer
|
2023-09-27 01:09:59 +03:00 |
loupzeur
|
da8b6bbce1
|
fix: xtts not taking into account device flag (#2951)
* fix: xtts not taking into account device flag
* Style changes
---------
Co-authored-by: Julian Weber <julian.weber@hotmail.fr>
|
2023-09-20 09:57:02 +02:00 |
Eren Gölge
|
4033db5f4b
|
🔥 XTTS implementation
|
2023-09-13 17:51:24 +02:00 |
Edresson Casanova
|
4d3f23b5d3
|
Add CML-TTS dataset YourTTS training recipe (#2934)
|
2023-09-12 11:49:14 +02:00 |
Aleś Bułojčyk
|
fead04f779
|
Add phonemizer for Belarusian language (#2856)
|
2023-08-28 11:20:45 +02:00 |
Eren Gölge
|
a7a96d08dd
|
Fix loading Bark (#2893)
* Fixup hubert path
* Make style
|
2023-08-26 11:59:00 +02:00 |
Jake Tae
|
409db505d2
|
Add device support in TTS and Synthesizer (#2855)
* fix: resolve merge conflicts
* fix: retain backwards compatability in functions
* feature: utilize device for voice transfer
* feature: use device for vocoder
* chore: cleanup vocoder cpu logic
* fix: add necessary vocoder output device check
* fix: add necessary vocoder output device check
* fix: indentation
* fix: check if waveform is pt tensor before cpu conversion
---------
Co-authored-by: Jake Tae <jaketae@Jakes-MacBook-Pro-2.local>
|
2023-08-14 21:04:44 +02:00 |
Eren Gölge
|
3a104d5c49
|
Update Studio API for XTTS (#2861)
* Update Studio API for XTTS
* Update the docs
* Update README.md
* Update README.md
Update README
|
2023-08-13 12:04:12 +02:00 |
Eren G??lge
|
37b558ccb9
|
Make style
|
2023-08-11 12:55:23 +02:00 |
Eren G??lge
|
9a8352b8da
|
Fix import error with Bark
|
2023-08-11 03:33:59 +02:00 |
Eren Gölge
|
4186f42b21
|
Handle missing JA phonemizer (#2843)
* Handle missing JA phonemizer
* Make style
|
2023-08-07 13:19:38 +02:00 |
Javier
|
4e7f8cd021
|
Add fairseq onnx support and strict configuration, fixes some onnx errors (#2831)
|
2023-08-04 11:02:59 +02:00 |
Eren Gölge
|
69f080eb47
|
Fix DelightfulTTS (#2823)
* Fix tests
* Make style
|
2023-07-31 13:52:45 +02:00 |
Eren Gölge
|
483888b9d8
|
Add kwargs to ignore extra arguments w/o error (#2822)
|
2023-07-31 11:37:35 +02:00 |
Aleś Bułojčyk
|
d124f78430
|
Recipe for Belarusian TTS (#2756)
* Changes from jhlfrfufyfn <jhlfrfufyfn@gmail.com>
* Recipe for Belarusian TTS
---------
Co-authored-by: jhlfrfufyfn <jhlfrfufyfn@gmail.com>
|
2023-07-31 10:26:21 +02:00 |
Javier
|
c140df5a58
|
Adds multi-language support for VITS onnx, fixes onnx inference error when speaker_id is None or not passed, fixes onnx exporting for models with init_discriminator=false (#2816)
|
2023-07-31 10:19:49 +02:00 |