Commit Graph

41 Commits

Author SHA1 Message Date
Eren Gölge
e62d3c5cf7 Use absolute imports for tts configs and models 2021-10-21 16:29:06 +00:00
Eren Gölge
4dbe7ed0de Fix all-zero duration case for GlowTTS 2021-10-01 09:24:26 +00:00
Eren Gölge
2766dd1d6e Fix #813 - GlowTTS training (#814)
* Fix #813

* Update glow_tts recipe

* Fix glow-tts test

* Linter fix

* Run data dep init only in training
2021-09-17 20:06:55 +02:00
Eren Gölge
1e7db32e90 Test FastPitch train 2021-09-11 10:19:47 +00:00
Eren Gölge
26f76fce22 Remove SpeedySpeech from .models.json 2021-09-10 17:47:27 +00:00
Eren Gölge
7ec23e69d4 Skip TF tests on GPU 2021-09-10 17:28:58 +00:00
Eren Gölge
1ebf9ec6bf Remove speedy_speech implementation 2021-09-10 17:28:20 +00:00
Eren Gölge
ed4b1d8514 Test TTS.tts.utils.helpers 2021-09-10 08:25:21 +00:00
Eren Gölge
8b7e094bde Implement forward_tts
- Generic API for feed-forward TTS models (FastPitch, SpeedySpeech)

- Tests for `forward-tts`

- Edit  FastPitchConfig and SpeedySpeechConfig to use `forward_tts`
2021-09-10 08:24:33 +00:00
Eren Gölge
4761853c5c Fix imports 2021-09-08 13:34:40 +00:00
Eren Gölge
e72c265cd4 Fix linter issues 2021-09-06 15:16:58 +00:00
Eren Gölge
076d0cb258 Add tests for certain FastPitch functions 2021-09-06 15:16:58 +00:00
Eren Gölge
c312acac7d Implement VITS model 🚀
VITS model implementation built on Glow TTS and HiFiGAN
layers.
2021-08-09 18:02:36 +00:00
Eren Gölge
003e5579e8 Enable custom_symbols in text processing
Models can define their own custom symbols lists with custom
`make_symbols()`
2021-08-09 18:02:36 +00:00
Eren Gölge
e4648ffef1 Fix multi-speaker init of Tacotron models & tests 2021-08-09 18:02:36 +00:00
Agrin Hilmkil
ced4cfdbbf Allow saving / loading checkpoints from cloud paths (#683)
* Allow saving / loading checkpoints from cloud paths

Allows saving and loading checkpoints directly from cloud paths like
Amazon S3 (s3://) and Google Cloud Storage (gs://) by using fsspec.

Note: The user will have to install the relevant dependency for each
protocol. Otherwise fsspec will fail and specify which dependency is
missing.

* Append suffix _fsspec to save/load function names

* Add a lower bound to the fsspec dependency

Skips the 0 major version.

* Add missing changes from refactor

* Use fsspec for remaining artifacts

* Add test case with path requiring fsspec

* Avoid writing logs to file unless output_path is local

* Document the possibility of using paths supported by fsspec

* Fix style and lint

* Add missing lint fixes

* Add type annotations to new functions

* Use Coqpit method for converting config to dict

* Fix type annotation in semi-new function

* Add return type for load_fsspec

* Fix bug where fs not always created

* Restore the experiment removal functionality
2021-08-09 18:02:36 +00:00
Eren Gölge
626c9d41e6 Update tests for the new trainer API 2021-06-28 17:03:19 +02:00
Eren Gölge
00c82c516d rename to 2021-06-28 17:03:19 +02:00
Eren Gölge
25238e0658 fix glow-tts inference() 2021-06-28 17:03:19 +02:00
Eren Gölge
82582993cc use one testing sentence in tts tests 2021-06-28 17:03:19 +02:00
Eren Gölge
419735f440 refactor and fix multi-speaker training in Trainer and Tacotron models 2021-06-28 17:03:19 +02:00
Eren Gölge
269e5a734e add max_decoder_steps argument to tacotron models 2021-06-28 17:03:19 +02:00
Eren Gölge
db6a97d1a2 rename external speaker embedding arguments as d_vectors 2021-06-28 17:03:19 +02:00
Eren Gölge
1443d03af1 update test for the new input output API of the tts models 2021-06-28 17:03:19 +02:00
Eren Gölge
6c495c6a6e fix glow-tts inference and forward functions for handling cond_input
and refactor its test
2021-06-28 17:03:19 +02:00
Eren Gölge
b500338faa make style 2021-06-28 17:03:19 +02:00
Eren Gölge
7dff6be871 update tts training tests to use the trainer 2021-06-28 17:03:19 +02:00
Eren Gölge
9134c7dfb6 update sequence_mask import globally 2021-06-28 17:03:19 +02:00
Eren Gölge
6c7bbcaef0 Use en-us for testing phoneme models 2021-06-25 16:52:17 +02:00
Eren Gölge
0c14278c30 reorg test files 2021-06-02 11:40:26 +02:00
Eren Gölge
73b4083c6c Merge pull request #502 from kaiidams/kaiidams/kokoro
Japanese Tacotron 2 model
2021-06-02 10:20:08 +02:00
Katsuya Iida
1cc18d1972 Move unittest of Japanese phonemizer. 2021-06-01 18:51:34 +09:00
Eren Gölge
925c08cf95 replace unidecode with anyascii 2021-05-27 14:02:44 +02:00
Eren Gölge
9b706c5583 enable phonemes in test to match the attention masks 2021-05-19 03:15:54 +02:00
Eren Gölge
8a7c40736c set use_phonemes false 2021-05-19 01:27:26 +02:00
Eren Gölge
19fb1d743d style update 2021-05-11 11:30:00 +02:00
Eren Gölge
5aee30443f refactoring tests after Coqpit 2021-05-11 11:30:00 +02:00
Eren Gölge
bcebd69d09 remove bash tts training tests 2021-05-11 11:29:17 +02:00
Eren Gölge
51a7e06945 glow_tts_config.py and train test on python 2021-05-11 11:29:17 +02:00
Eren Gölge
c6df8de80a remove output train folder at the end of the test 2021-05-11 11:29:17 +02:00
Eren Gölge
35341d5482 move bash script based tests to python with coqpit 2021-05-11 11:29:17 +02:00