tsukumi
aa0f9308b1
Refactor: remove dependencies on libraries not required for style_bert_vits2 as a library
...
librosa: Originally not used under style_bert_vits2/.
pyannote.audio: Required only when using the "infer style vector from audio" function during inference, but it is currently almost unused.
scipy: Because it was used in only one utility function that was not needed outside of training.
2024-04-25 00:31:14 +00:00
tsukumi
28f254f449
Improve: remove Gradio dependency from style_bert_vits2 as a library
2024-04-23 05:45:11 +00:00
tsukumi
9d15d5763d
Refactor: run "hatch run style:fmt"
2024-04-19 04:17:27 +00:00
tsukumi
797c354b1b
Add: the ability to specify a phoneme sequence representing the reading of the text to be read during speech synthesis
...
With this feature, it is possible to specify individual readings for homonyms such as "明日 (ashita/asu)" while maintaining the Kanji representation of the read text.
2024-04-19 04:09:21 +00:00
litagin02
7a34fd24c1
Fix gradio ver for json serialize error
2024-03-29 21:51:04 +09:00
litagin02
6d5b854cf2
Fix: invalid path for generating neutral style
2024-03-22 15:54:22 +09:00
litagin02
4afe92d75f
Fix: gen style in beginning of train for nested folders
2024-03-22 08:27:43 +09:00
litagin02
d7a3e5696c
docs
2024-03-19 20:16:07 +09:00
litagin02
70d252bcc7
Feat: preserve relative path when resample
2024-03-19 20:14:19 +09:00
litagin02
7c484c7835
Powershell version
2024-03-19 08:51:41 +09:00
litagin02
8c9eb74335
Fix colab
2024-03-18 09:02:50 +09:00
litagin02
8d6eec9d1b
docs
2024-03-16 20:25:15 +09:00
litagin02
defb5253aa
Fix errorcheck
2024-03-16 18:41:29 +09:00
litagin02
251b075942
Remove debug pause
2024-03-16 18:27:28 +09:00
litagin02
baeecbc2b9
Clean
2024-03-16 18:25:56 +09:00
litagin02
94e29d1337
Remove debug pause
2024-03-16 18:25:33 +09:00
litagin02
76be727b2e
Bump ver
2024-03-16 18:22:35 +09:00
litagin02
b363a8866e
Remove debugging pause
2024-03-16 18:03:04 +09:00
litagin02
242e7ee2f0
Fix activating venv
2024-03-16 17:26:05 +09:00
litagin02
f2cc879603
Fix: eneabledelayedexpansion for error code
2024-03-16 16:49:22 +09:00
litagin02
5eef8843cc
Improve bat, replace MinGit with PortableGit
2024-03-16 15:25:19 +09:00
litagin02
8a8cd1dcaf
Feat: using MinGit for bat install and update
2024-03-16 11:56:48 +09:00
litagin02
386d122cc7
Change webui/ to gradio_tabs/ to avoid conflict
2024-03-15 22:41:19 +09:00
litagin02
9986ce3ca4
Merge branch 'dev'
2024-03-15 21:50:20 +09:00
litagin02
5bafd7ffe9
docs
2024-03-15 21:50:04 +09:00
litagin02
c8f4b82157
Merge pull request #97 from litagin02/dev
...
Ver 2.4
2024-03-15 21:44:39 +09:00
litagin02
ab4020545e
Bump torch ver and docs
2024-03-15 21:43:57 +09:00
litagin02
14c6805337
Update hatch setting and fmt
2024-03-15 21:36:53 +09:00
litagin02
2ee4f4ac86
Change dev to master in bat
2024-03-15 21:27:22 +09:00
litagin02
1a8a7edb9c
Docs and bump default pytorch version to 2.2.1 latest
2024-03-15 21:25:24 +09:00
litagin02
e42991f7e3
Remove loading bert since necessary model is loaded automatically
2024-03-15 21:10:24 +09:00
litagin02
f796af5fbb
Remove loading bert since necesary model is loaded automatically
2024-03-15 21:07:56 +09:00
litagin02
5100b4a57e
docs
2024-03-15 20:30:22 +09:00
litagin02
3efcb98858
docs
2024-03-15 20:16:58 +09:00
litagin02
d808cd635d
Delete num_process option for slice for simplicity
2024-03-15 19:58:16 +09:00
litagin02
d808793960
Change default HF whisper batch size to 16
2024-03-15 19:56:55 +09:00
litagin02
b02b882c04
Feat: support various audio format in slice.py
2024-03-15 12:53:24 +09:00
litagin02
432edcc52b
Bump ver, rename configs_jp_extra to config_jp_extra for consistency
2024-03-15 12:34:54 +09:00
litagin02
3d8b60c03c
Refactor
2024-03-15 12:27:46 +09:00
litagin02
867855ace9
Refactor, improve: use pathlib, allow audios other than wavs in resample
2024-03-15 11:10:23 +09:00
litagin02
5c1e791b9a
Add cleaning bat script
2024-03-15 10:30:22 +09:00
litagin02
73b01f7172
Add another wave dash for long symbol
2024-03-14 23:31:16 +09:00
litagin02
1b72023e02
Require torch>=2.1
2024-03-14 19:15:21 +09:00
litagin02
1d9b91fd2a
Update torch req to torch>=2.1 from torch==2.1.x
...
because this req is only needed in colab or linux, and it's no problem for torch 2.2.x for linux.
2024-03-14 19:02:55 +09:00
litagin02
51e246658d
Change torch==2.1 to torch >=2.1
2024-03-14 18:30:21 +09:00
litagin02
2eb489f91e
docs
2024-03-14 18:29:06 +09:00
litagin02
6f42a1514f
Add ngram_size option
2024-03-14 17:42:29 +09:00
litagin02
8c95f0ff75
Fix hf whisper
2024-03-14 16:45:31 +09:00
litagin02
a5540bdb2e
Clean
2024-03-14 16:25:04 +09:00
litagin02
2996a0b195
docs
2024-03-14 15:41:10 +09:00
