Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update models (Rebased) #1078

Closed
wants to merge 67 commits into from
Closed
Changes from 1 commit
Commits
Show all changes
67 commits
Select commit Hold shift + click to select a range
c971e06
Refactor Synthesizer class for TTSTokenizer
erogol Nov 16, 2021
c9142eb
Refactor TTSDataset to use TTSTokenizer
erogol Nov 16, 2021
da13f46
Refactor synthesis.py for TTSTokenizer
erogol Nov 16, 2021
2588e82
Refactor GlowTTS model and recipe for TTSTokenizer
erogol Nov 16, 2021
e1db180
Update imports for symbols -> characters
erogol Nov 17, 2021
66cad5b
Update for tokenizer API
erogol Nov 24, 2021
4884169
Refactor TTSDataset ⚡️
erogol Nov 30, 2021
580b99e
Refactorin VITS for the tokenizer API
erogol Nov 30, 2021
7c46d5e
Update data loader tests
erogol Dec 1, 2021
033dedf
Add init_from_config
erogol Dec 7, 2021
29ff0f6
Make lint
erogol Dec 7, 2021
49fef8d
Allow None pad and blank tokens
erogol Dec 7, 2021
7deadfe
Use the same phonemizer for `en` to `en-us`
erogol Dec 7, 2021
83b9fda
Pass samples to init_from_config in SpeakerManager
erogol Dec 7, 2021
ae96243
Update VITS for the new API
erogol Dec 7, 2021
160115b
Update Tacotron models
erogol Dec 7, 2021
0ff11d4
Update ForwardTTS
erogol Dec 7, 2021
f46ad54
Update AlignTTS
erogol Dec 7, 2021
a8a8365
Update GlowTTS
erogol Dec 7, 2021
4640d59
Update setup_model
erogol Dec 7, 2021
f8fbbd4
Update BaseTTS config
erogol Dec 7, 2021
ab413fd
Update train_tts.py
erogol Dec 7, 2021
cee01a6
Update ljspeech recipes
erogol Dec 7, 2021
e9448ca
Update loader tests
erogol Dec 7, 2021
c974633
Update tests
erogol Dec 7, 2021
848fd73
Update spec extractor
erogol Dec 7, 2021
3a15e2f
Update ljspeech download
erogol Dec 7, 2021
9338c7b
Update pylintrc
erogol Dec 7, 2021
672d766
Update VCTK formatter
erogol Dec 8, 2021
cecce06
Add file_ext args to resample.py
erogol Dec 8, 2021
95df38c
Update VCTK recipes
erogol Dec 8, 2021
b4cbf2e
Fix `too many open files`
erogol Dec 8, 2021
bbad03e
Update recipes README.md
erogol Dec 8, 2021
13a8f71
Delete `use_espeak_phonemes` from tests
erogol Jan 7, 2022
90fe858
Fix synthesis.py 🔧
erogol Jan 7, 2022
bddcc9d
Fixes small compat. issues
erogol Jan 7, 2022
c35b0c9
Update Vits for the new model API
erogol Jan 7, 2022
b2e1420
Update train_tts for the new API
erogol Jan 7, 2022
83b6cf5
Extend glow_tts model tests
erogol Jan 12, 2022
5a1d2de
Add verbose option to AudioProcessor
erogol Jan 12, 2022
3c9e518
Fix tokenizer init_from_config
erogol Jan 12, 2022
9d9a5b3
Fix glow_tts_config missing field
erogol Jan 12, 2022
79a5400
Add get_tests_data_path
erogol Jan 12, 2022
0919578
Make lint
erogol Jan 12, 2022
26be609
Extend unittests
erogol Jan 13, 2022
4b612d7
Make lint
erogol Jan 13, 2022
2433626
Fix tests
erogol Jan 14, 2022
911b2db
Fix docstring
erogol Jan 14, 2022
2472d43
Allow padding for shorter segments
erogol Jan 21, 2022
8c555d3
Implement `start_by_longest` option for TTSDatase
erogol Jan 21, 2022
c3ae114
Refactor VITS model
erogol Jan 21, 2022
c94112f
Update GAN model
erogol Jan 25, 2022
2386d80
Take file extension as an argument
erogol Jan 25, 2022
269f8c6
Update synthesizer to use iinit_from_config
erogol Jan 25, 2022
a27133d
Add pitch_fmin pitch_fmax args to the audio
erogol Jan 25, 2022
2303c91
Plot pitch over input characters
erogol Jan 25, 2022
a8352d9
Update language manager
erogol Jan 25, 2022
8397502
Update forwardtts
erogol Jan 25, 2022
c2d5be5
Fix dataset preprocessing
erogol Jan 25, 2022
ad98306
Update FastPitchConfig
erogol Jan 25, 2022
f966a45
Make style
erogol Jan 25, 2022
153c875
Update AnalyzeDataset notebook
erogol Jan 25, 2022
f912206
Load right char class dynamically
erogol Jan 28, 2022
0b8acaf
Add new speakers to the vits model
erogol Jan 28, 2022
a164485
Fix up
erogol Jan 28, 2022
6c55245
Fix VCTK VITS recipe
erogol Jan 28, 2022
a68fb76
Set `drop_last`
erogol Jan 28, 2022
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Fix tests
erogol committed Jan 14, 2022
commit 24336262f5093a76e0b2a2f0e1794bfcd40e5d43
8 changes: 5 additions & 3 deletions TTS/bin/find_unique_phonemes.py
Original file line number Diff line number Diff line change
@@ -7,14 +7,16 @@

from TTS.config import load_config
from TTS.tts.datasets import load_tts_samples
from TTS.tts.utils.text import text2phone
from TTS.tts.utils.text.phonemizers.gruut_wrapper import Gruut


phonemizer = Gruut(language="en-us")


def compute_phonemes(item):
try:
text = item[0]
language = item[-1]
ph = text2phone(text, language, use_espeak_phonemes=c.use_espeak_phonemes).split("|")
ph = phonemizer.phonemize(text).split("|")
except:
return []
return list(set(ph))
2 changes: 0 additions & 2 deletions tests/aux_tests/test_find_unique_phonemes.py
Original file line number Diff line number Diff line change
@@ -39,7 +39,6 @@ def test_espeak_phonemes():
num_eval_loader_workers=0,
text_cleaner="english_cleaners",
use_phonemes=True,
use_espeak_phonemes=True,
phoneme_language="en-us",
phoneme_cache_path="tests/data/ljspeech/phoneme_cache/",
run_eval=True,
@@ -64,7 +63,6 @@ def test_no_espeak_phonemes():
num_eval_loader_workers=0,
text_cleaner="english_cleaners",
use_phonemes=True,
use_espeak_phonemes=False,
phoneme_language="en-us",
phoneme_cache_path="tests/data/ljspeech/phoneme_cache/",
run_eval=True,