Jim O'Regan 4bc541705a add a cleaner for the mmconv data ...

Different versions of espeak represent things differently, it seems
(also, there are some distinctions none of our speakers make, so
normalising those away reduces perplexity a tiny amount).

2024-10-03 17:18:58 +00:00

..

data

Adding the possibility to train with durations

2024-05-27 13:24:21 +02:00

hifigan

Initial commit

2023-09-16 17:51:36 +00:00

models

Adding the possibility to train with durations

2024-05-27 13:24:21 +02:00

onnx

- Fixed several bugs. Thanks @shivammehta25 for the suggestions

2023-09-26 14:21:17 +02:00

text

add a cleaner for the mmconv data

2024-10-03 17:18:58 +00:00

utils

Adding the possibility to train with durations

2024-05-27 13:24:21 +02:00

__init__.py

Initial commit

2023-09-16 17:51:36 +00:00

app.py

Updating different url for hifigan as well

2024-01-12 11:21:51 +00:00

cli.py

Fixing batched synthesis for multispeaker model

2024-05-27 13:40:02 +02:00

train.py

Initial commit

2023-09-16 17:51:36 +00:00

VERSION

removing diffuser versioning

2024-08-09 18:28:56 +02:00