Commit Graph

221 Commits

Author SHA1 Message Date
Edresson Casanova 1a9ca35e14 Make style 2023-11-06 09:18:07 -03:00
Eren G??lge b094979f1a Make style 2023-11-06 11:41:23 +01:00
Eren G??lge b47afc5275 Update model entry 2023-11-06 11:38:58 +01:00
Eren G??lge c182535e2a Make prompt embedding configurable 2023-11-06 11:37:08 +01:00
Edresson Casanova cff8542012 Bug Fix on XTTS v2.0 training 2023-11-06 11:37:08 +01:00
Edresson Casanova 32796fdfc1 Bug fix on gpt forward 2023-11-06 11:37:08 +01:00
Edresson Casanova a032d9877b Bug fix masking with XTTS perceiver 2023-11-06 11:37:08 +01:00
Edresson Casanova 5df8f76b0c Update XTTS docs 2023-11-06 11:37:08 +01:00
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 c1133724a1 Move lang token add to tokenizer 2023-10-26 14:52:13 +02:00
Edresson Casanova 01839af926 Bug fix on XTTS masking training 2023-10-24 18:30:14 -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 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
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
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 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
Eren Gölge 4033db5f4b 🔥 XTTS implementation 2023-09-13 17:51:24 +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
Eren Gölge 483888b9d8
Add kwargs to ignore extra arguments w/o error (#2822) 2023-07-31 11:37:35 +02:00
logan hart 6fdb88f8e2
Add Delightful-TTS implementation (#2095)
* add configs

* Update config file

* Add model configs

* Add model layers

* Add layer files

* Add layer modules

* change config names

* Add emotion manager

* fIX missing ap bug

* Fix missing ap bug

* Add base TTS e2e class

* Fix wrong variable name in load_tts_samples

* Add training script

* Remove range predictor and gaussian upsampling

* Add helper function

* Add vctk recipe

* Add conformer docs

* Fix linting in conformer.py

* Add Docs

* remove duplicate import

* refactor args

* Fix bugs

* Removew emotion embedding

* remove unused arg

* Remove emotion embedding arg

* Remove emotion embedding arg

* fix style issues

* Fix bugs

* Fix bugs

* Add unittests

* make style

* fix formatter bug

* fix test

* Add pyworld compute pitch func

* Update requirments.txt

* Fix dataset Bug

* Chnge layer norm to instance norm

* Add missing import

* Remove emotions.py

* remove ssim loss

* Add init layers func to aligner

* refactor model layers

* remove audio_config arg

* Rename loss func

* Rename to delightful-tts

* Rename loss func

* Remove unused modules

* refactor imports

* replace audio config with audio processor

* Add change sample rate option

* remove broken resample func

* update recipe

* fix style, add config docs

* fix tests and multispeaker embd dim

* remove pyworld

* Make style and fix inference

* Split tts tests

* Fixup

* Fixup

* Fixup

* Add argument names

* Set "random" speaker in the model Tortoise/Bark

* Use a diff f0_cache path for delightfull tts

* Fix delightful speaker handling

* Fix lint

* Make style

---------

Co-authored-by: loganhart420 <loganartpersonal@gmail.com>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
2023-07-24 13:41:26 +02:00
Eren Gölge 0de12ec5aa
API tests (#2790)
* Separate API tests and only run when uplifted

* Make style
2023-07-24 12:14:21 +02:00
Eren Gölge 672ec3b35e
Fix #2749 (#2750) 2023-07-08 11:40:44 +02:00
Eren Gölge 7b5c8422c8
Export multispeaker onnx (#2743) 2023-07-06 13:36:50 +02:00
Eren G??lge 91cc11d636 Remove commented codes 2023-06-28 12:14:37 +02:00
Eren G??lge 6b9ebf5aab Merge branch 'p3_11' into dev 2023-06-28 12:13:04 +02:00
Eren Gölge c844b6570a
Inference API for 🐶Bark (#2685)
* Add bark requirements

* Draft Bark implementation

* Download HF models

* Update synthesizer

* Add bark model

* Make style

* Update pylintrc

* Update model URLs

* Update Bark Config

* Fix here and ther

* Make style

* Make lint

* Update requirements

* Update requirements
2023-06-28 11:55:27 +02:00
Eren G??lge 17ac188958 Drop fairseq for Hubert 2023-06-26 19:27:48 +02:00
Eren G??lge c03768bb53 Make style 2023-06-26 17:16:26 +02:00
Eren Gölge fff8b762bc
Merge branch 'dev' into bark 2023-06-21 15:49:05 +02:00
Eren G??lge cf98ae04df Make lint 2023-06-21 12:05:08 +02:00
Eren G??lge 3b9fca2398 Make style 2023-06-21 12:02:06 +02:00
Eren G??lge 0f8932a6a9 Fix here and ther 2023-06-21 11:59:27 +02:00