Commit Graph

1742 Commits

Author SHA1 Message Date
Eren G??lge a13b1352a4 Fixup 2023-06-26 19:30:26 +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 G??lge a1c431e6a9 Fixups 2023-06-26 12:55:18 +02:00
Eren G??lge a58fb6c01b Update requirements 2023-06-22 13:53:19 +02:00
Eren G??lge e888e8a56d Fix manage 2023-06-22 10:13:20 +02:00
Eren Gölge fff8b762bc
Merge branch 'dev' into bark 2023-06-21 15:49:05 +02:00
Eren Gölge 4cf8652392
Fix Tortoise load (#2697)
* Handle missing gpt weights

* Make style

* Fix lint
2023-06-21 15:42:01 +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
Eren G??lge 03c347b7f3 Update Bark Config 2023-06-21 11:58:18 +02:00
Eren G??lge 695e862aad Update model URLs 2023-06-21 11:57:46 +02:00
Eren G??lge f4c88ed677 Make style 2023-06-19 14:22:32 +02:00
Eren G??lge 37b708dac7 Add bark model 2023-06-19 14:16:06 +02:00
Eren G??lge 2364c38d16 Update synthesizer 2023-06-19 14:15:21 +02:00
Eren G??lge 5a31fad502 Download HF models 2023-06-19 14:14:04 +02:00
Eren G??lge f59da4dba5 Draft Bark implementation 2023-06-12 14:32:39 +02:00
Tsai Meng-Ting d65819422b
Update stochastic_duration_predictor.py (#2663)
fix a typo
2023-06-12 11:10:54 +02:00
Eren Gölge 49cf6a5d62 Bump up to v0.14.3 2023-06-06 09:41:59 +02:00
Eren Gölge 8e415732dd Fixup 2023-06-06 09:41:46 +02:00
Eren Gölge 547a72c97d Fixup 2023-06-05 22:38:56 +02:00
Eren Gölge a494f0c92a Bump up to v0.14.1 2023-06-05 11:29:10 +02:00
Eren Gölge 50b1074779 Make `tts` ready 2023-06-05 11:29:10 +02:00
Eren Gölge e785d101a1
Port Fairseq TTS models (#2628)
* Load fairseq models

* Add docs and missing files

* Managing fairseq models and docs for API

* Make style

* Use scarf URL

* Add tests

* Fix URL

* Pass cpu

* Make lint

* Fixup

* Make lint

* fixup

* Fixup

* Change tokenization order

* Update README

* Fixup

* Fixup
2023-06-05 11:15:13 +02:00
Shukrullo Turgunov 0d5e68a09f
fix typo (#2647)
* fix typo

* typo fix
2023-06-05 09:58:16 +02:00
Reuben Morais 23a7a9a363
Fetch all built-in speakers (#2626) 2023-05-22 17:28:08 +02:00
Eren Gölge aef7f6d980 Bump up to v0.14.1 2023-05-18 11:13:09 +02:00
Eren Gölge 9e99e0f42d Disable reduction 2023-05-18 11:12:51 +02:00
Eren Gölge bc0a532c7a
Bump up to v0.14.0 2023-05-16 10:08:41 +02:00
Eren Gölge 4de797bb11
Draft ONNX export for VITS (#2563)
* Draft ONNX export for VITS

Could not get it work to output variable length sequence

* Fixup for onnx constant output

* Make style

* Remove commented code
2023-05-16 01:07:56 +02:00
manmay nakhashi a3d5801c44
Tortoise TTS inference (#2547)
* initial commit

* Tortoise inference

* revert path change

* style fix

* remove accidental remove

* style fixes

* style fixes

* removed unwanted assests and deps

* remove changes

* remove cvvp

* style fix black

* added tortoise config and updated config and args, refactoring the code

* added tortoise to api

* Pull mel_norm from url

* Use TTS cleaners

* Let download model files

* add ability to pass tortoise presets through coqui api

* fix tests

* fix style and tests

* fix tts commandline for tortoise

* Add config.json to tortoise

* Use kwargs

* Use regular model api for loading tortoise

* Add load from dir to synthesizer

* Fix Tortoise floats

* Use model_dir when there are multiple urls

* Use `synthesize` when exists

* lint fixes and resolve preset bug

* resolve a download bug and update model link

* fix json

* do tortoise inference from voice dir

* fix

* fix test

* fix speaker id and remove assests

* update inference_tests.yml

* replace inference_test.yml

* fix extra dir as None

* fix tests

* remove space

* Reformat docstring

* Add docs

* Update docs

* lint fixes

---------

Co-authored-by: Eren Gölge <egolge@coqui.ai>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
2023-05-16 00:58:21 +02:00
Eren Gölge 9b5822d625
Update VAD for silence trimming. (#2604)
* Update vad for mp3 and fault tolerance

* Make style

* Remove importt

* Remove stupid defaults
2023-05-11 11:09:23 +02:00
Eren Gölge dfb51e06b2
Add jenny model (#2603) 2023-05-08 12:05:40 +02:00
Michael Görner 27e237ed08
use default_factory for audio parameter (#2576)
Python 3.11 complains about the mutable default and other members
were already adapted to use the factory, so I expect this line just
went unnoticed until now.
2023-05-08 11:17:36 +02:00
prakharpbuf c1875f68df
typos and minor fixes (#2508)
* Update tacotron1-2.md

* Update README.md

* Update Tutorial_2_train_your_first_TTS_model.ipynb

* Update synthesizer.py

There is no arg called --speaker_name

* Update formatting_your_dataset.md

* Update AnalyzeDataset.ipynb

* Update AnalyzeDataset.ipynb

* Update AnalyzeDataset.ipynb

* Update finetuning.md

* Update train_yourtts.py

* Update train_yourtts.py

* Update train_yourtts.py

* Update finetuning.md
2023-04-26 15:22:57 +02:00
Eren Gölge 2071088bab
Bump up to v0.13.3 2023-04-17 16:13:35 +02:00
Eren Gölge 1a6a5710fd Make lint 2023-04-17 15:02:56 +02:00
Eren Gölge a44a0e1fd2 Update model urls 2023-04-17 14:53:27 +02:00
Eren Gölge 2533a18d62 Add BN tests 2023-04-17 13:37:10 +02:00
Eren Gölge 2d49c05259 Remove import 2023-04-17 13:05:29 +02:00
Eren Gölge 5e5768d784 Fix API 2023-04-17 13:05:19 +02:00
Eren Gölge cd83991067 Add BN phonemizer 2023-04-17 12:54:00 +02:00
Eren Gölge 36be05290d Add models 2023-04-17 12:52:32 +02:00
Eren Gölge e4c5c27854
Bump up to v0.13.2 2023-04-14 10:23:39 +02:00
Eren Gölge dba5cec497
Merge pull request #2509 from coqui-ai/update_vad
Update VAD
2023-04-13 19:35:17 +02:00
Eren Gölge 5a9bda13f3 Make style 2023-04-13 14:19:06 +02:00
Eren Gölge c9375e4b8b Make style 2023-04-13 14:17:06 +02:00
Eren Gölge 758ef84cc2 Using 🐸Studio models with `tts` command 2023-04-13 14:14:41 +02:00
Eren G??lge 537dc0e933 Update VAD 2023-04-13 00:39:46 +02:00