tuna2134/sbv2-v2

Fork 0

Go to file

Stardust·减 12c9fb9ee8 Update train_ms.py

2023-08-21 17:17:40 +08:00

bert/chinese-roberta-wwm-ext-large

add bert

2023-07-21 12:22:49 +08:00

configs

Update config.json

2023-08-21 14:04:25 +08:00

filelists

fix

2023-07-28 12:47:44 +08:00

monotonic_align

init

2023-07-21 12:12:35 +08:00

text

Update cleaner.py

2023-08-04 09:48:22 +08:00

.gitignore

Initial commit

2023-07-21 12:02:46 +08:00

attentions.py

Update attentions.py

2023-08-21 12:49:20 +08:00

commons.py

init

2023-07-21 12:12:35 +08:00

data_utils.py

Update data_utils.py

2023-08-21 09:23:00 +08:00

LICENSE

Initial commit

2023-07-21 12:02:46 +08:00

losses.py

init

2023-07-21 12:12:35 +08:00

mel_processing.py

Update mel_processing.py

2023-08-21 10:03:31 +08:00

models.py

Update models.py

2023-08-21 08:32:39 +08:00

modules.py

Update modules.py

2023-08-20 16:35:50 +08:00

preprocess_text.py

Update preprocess_text.py

2023-08-21 08:43:34 +08:00

README.md

Update README.md

2023-08-03 18:39:17 +08:00

requirements.txt

Update requirements.txt

2023-08-03 18:23:43 +08:00

resample.py

init

2023-07-21 12:12:35 +08:00

server.py

Update server.py

2023-08-04 09:47:22 +08:00

spec_gen.py

Update spec_gen.py

2023-08-03 18:37:06 +08:00

train_ms.py

Update train_ms.py

2023-08-21 17:17:40 +08:00

transforms.py

init

2023-07-21 12:12:35 +08:00

utils.py

init

2023-07-21 12:12:35 +08:00

README.md

bert-vits

vits with bert

put pytorch_model.bin to bert/roberta_wwm_ext_large/
Then resample all audio to 44100Hz,generate filelists.
Please read the code in preprocess_text.py to generate the specified format filelist.
Run preprocess_text.py
Run spec_gen.py
Run train_ms.py(Only multi speaker training is supported)