tacotron2

mirror of https://github.com/malarinv/tacotron2 synced 2026-03-08 01:32:35 +00:00

Go to file

Malar Kannan 08ad9ce16e 1. clean-up redundant code

2. remove ffmpeg dependency using librosa api
3. remove waveglow submodule

2019-07-02 16:16:44 +05:30

text

text/symbols.py: updating symbols

2018-11-25 22:34:26 -08:00

.gitignore

1. create a class for the tts api

2019-07-01 14:47:55 +05:30

audio_processing.py

adding python files

2018-05-03 15:16:57 -07:00

corpus.txt

add a function to cache all responses from corpus.txt

2019-06-28 18:44:24 +05:30

data_utils.py

data_utils.py: rewrite

2018-11-25 22:32:47 -08:00

demo_client.py

1. clean-up redundant code

2019-07-02 16:16:44 +05:30

distributed.py

Fixing concatenation error for fp16 ditributed training

2019-02-01 09:55:59 +01:00

glow.py

1. clean-up redundant code

2019-07-02 16:16:44 +05:30

hparams.py

1. create a class for the tts api

2019-07-01 14:47:55 +05:30

layers.py

layers.py: rewrite

2018-11-25 22:33:32 -08:00

LICENSE

Update license such that it appears on repo fron tpage

2018-05-03 23:18:34 -07:00

logger.py

logger.py: using new pytorch api

2019-04-03 13:35:04 -08:00

loss_function.py

adding python files

2018-05-03 15:16:57 -07:00

model.py

model.py: renaming variables, removing dropout from lstm cell state, removing conversions now handled by amp

2019-04-03 13:36:35 -08:00

plotting_utils.py

adding python files

2018-05-03 15:16:57 -07:00

README.md

1. clean-up redundant code

2019-07-02 16:16:44 +05:30

requirements_dev.txt

1. create a class for the tts api

2019-07-01 14:47:55 +05:30

requirements.txt

clean-up for cpu-only inference

2019-06-28 09:46:46 +05:30

server.py

1. create a class for the tts api

2019-07-01 14:47:55 +05:30

stft.py

clean-up for cpu-only inference

2019-06-28 09:46:46 +05:30

train.py

clean-up for cpu-only inference

2019-06-28 09:46:46 +05:30

tts.py

1. clean-up redundant code

2019-07-02 16:16:44 +05:30

utils.py

clean-up for cpu-only inference

2019-06-28 09:46:46 +05:30

README.md

Setup

clone the repo

git clone https://github.com/agaralabs/tacotron2

cd to tacotron2 copy models from wolverine:

scp wolverine:/home/ubuntu/tacotron2/{checkpoint_15000,waveglow_256channels.pt} ./

scp wolverine:/home/ubuntu/tacotron2/waveglow ./

Wolverine Details:

Host wolverine
    Hostname 54.71.137.17
    User ubuntu
    IdentityFile ~/.ssh/id_hip_ml

install the dependencies pip install requirements.txt

Running:

python final.py