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 |
|