Commit Graph

2964 Commits

Author SHA1 Message Date
Eren Gölge
830306d2fd update extract_tts_spectrograms for the new model API 2021-06-22 13:12:52 +02:00
Eren Gölge
c673eb8ef8 correct import of load_meta_data
remove redundant import
2021-06-22 13:12:52 +02:00
Eren Gölge
f0a419546b fix Synthesized for the new synthesis() 2021-06-22 13:12:52 +02:00
Eren Gölge
c7ff175592 revert logging.info to print statements for trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
fd6afe5ae5 update setup_model.py imports 2021-06-22 13:12:52 +02:00
Eren Gölge
0c05318e8d update tts training tests to use the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
c82d91051d update align_tts.py model for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
4f66e816d1 update align_tts_loss for trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
8213ad8b5f update aling_tts_config for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
8dfd4c91ff update trainer.py for better logging handling, restoring models and
rename init_ functions with get_
2021-06-22 13:12:52 +02:00
Eren Gölge
fb9289d365 update synthesis.py for being more generic 2021-06-22 13:12:52 +02:00
Eren Gölge
f121b0ff5d update speedy_speech.py model for trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
843b3ba960 update speedy_speecy_config.py for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
c9790bee2c update tacotron model to return model_outputs 2021-06-22 13:12:52 +02:00
Eren Gölge
f09ec7e3a7 update glow-tts for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
3346a6d9dc update sequence_mask import globally 2021-06-22 13:12:52 +02:00
Eren Gölge
9765b1aa6b update glow_tts_config.py for setting the optimizer and the scheduler 2021-06-22 13:12:52 +02:00
Eren Gölge
6bf6543df8 typing annotation for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
57cdddef16 add trainer and train_tts 2021-06-22 13:12:52 +02:00
Eren Gölge
d769af9e3b remove truncated from synthesizer 2021-06-22 13:12:52 +02:00
Eren Gölge
570633ab80 update console logger 2021-06-22 13:12:52 +02:00
Eren Gölge
2ac6b824ca update synthesis.py for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
c9e5527070 remove tts.generic_utils as all the functions are moved to other files 2021-06-22 13:12:52 +02:00
Eren Gölge
2ab723cd10 update Tacotron models for the trainer 2021-06-22 13:12:52 +02:00
Eren Gölge
d6b6a15b5c add gradual_training argument to tacotron.py 2021-06-22 13:12:52 +02:00
Eren Gölge
118a7f2b43 import missings for tacotron.py 2021-06-22 13:12:52 +02:00
Eren Gölge
c98149d488 mode setup_model() to models/__init__.py 2021-06-22 13:12:52 +02:00
Eren Gölge
86edf6ab0e add sequence_mask to utils.data 2021-06-22 13:12:52 +02:00
Eren Gölge
c61486b1e3 setup_loss() in layer/__init__.py 2021-06-22 13:12:52 +02:00
Eren Gölge
f07209d2e0 rename preprocess.py -> formatters.py 2021-06-22 13:12:52 +02:00
Eren Gölge
facb782851 move load_meta_data and related functions to datasets/__init__.py 2021-06-22 13:12:52 +02:00
Eren Gölge
b9d4355d20 set test_sentences in config 2021-06-22 13:12:52 +02:00
Eren Gölge
7bdd0eb72f trainer-API updates 2021-06-22 13:12:52 +02:00
Eren Gölge
0f284841d1 rename MyDataset -> TTSDataset 2021-06-22 13:12:52 +02:00
Eren Gölge
d245b5d48f bump up v0.0.15.1 v0.0.15.1 2021-06-08 09:21:01 +02:00
Eren Gölge
d0eb2e636f Merge pull request #557 from coqui-ai/add-missing-version-file
add missing VERSION to manifest
2021-06-08 09:19:29 +02:00
Eren Gölge
ed6e109aec add missing VERSION to manifest 2021-06-08 09:17:05 +02:00
Eren Gölge
b8b79a5e5a fix use_cuda bug in server.py v0.0.15 2021-06-04 14:02:53 +02:00
Eren Gölge
203ab855c3 bump up to v0.0.15 2021-06-04 13:52:54 +02:00
Eren Gölge
06a7088557 Merge pull request #532 from coqui-ai/auto-pypi-upload
auto upload to pypi on release
2021-06-04 13:30:41 +02:00
Eren Gölge
ba9bcf7c6b auto upload to pypi on release 2021-06-04 12:20:06 +02:00
Eren Gölge
e66753bd0d fixup! new japanese model placeholder in .models.json 2021-06-03 18:04:28 +02:00
Eren Gölge
bd434636a9 new japanese model placeholder in .models.json 2021-06-02 15:54:37 +02:00
Eren Gölge
401fbd8978 bump up to v0.0.15 2021-06-02 11:48:17 +02:00
Eren Gölge
db48c69f0f reduce fullband melgan model size for testing 2021-06-02 11:44:53 +02:00
Eren Gölge
4baa59d732 comment requirements.txt for japanese deps 2021-06-02 11:44:53 +02:00
Eren Gölge
49c5e5d820 maket style japanese PR 2021-06-02 11:44:46 +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
Eren Gölge
ea31215087 Merge pull request #520 from SanjaESC/patch-1
fix taco2 speaker-embeddings dimension during inference
2021-06-02 09:32:24 +02:00