PublicMirrors/voice-changer
1
0
Fork 0
mirror of https://github.com/w-okada/voice-changer.git synced 2025-01-23 13:35:12 +03:00
Code Issues Actions Packages Projects Releases Wiki Activity

WIP:Docker update

Browse Source
This commit is contained in:
wataru 2023-02-01 11:18:10 +09:00
parent 161c25aea9
commit 080fa52059
3 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docker_trainer/Dockerfile
View File

@ -5,7 +5,6 @@ ARG DEBIAN_FRONTEND=noninteractive
RUN apt-get -y update && apt-get install -y emacs git curl python3-pip libsndfile1-dev ffmpeg
RUN git clone --depth 1 -b v1.5.0.0_SiFiGAN https://github.com/isletennos/MMVC_Trainer.git
ADD /model/D_v15_best.pth /MMVC_Trainer/fine_model/
ADD /model/G_v15_best.pth /MMVC_Trainer/fine_model/
@ -26,6 +25,8 @@ ADD /warmup.py /
RUN python3 warmup.py
WORKDIR /MMVC_Trainer/
RUN cp -r /MMVC_Trainer/configs /MMVC_Trainer/configs_org
# python3 normalize.py True
# python3 create_dataset.py -f train_config -s 24000 -m dataset/multi_speaker_correspondence.txt
# tensorboard --logdir logs --port 5000

1
docker_trainer/README.md
View File

@ -48,6 +48,7 @@ trainer/dataset/
(4) Docker内で次のコマンドを実行
batch sizeは適宜調整
```sh
$ cp configs_org/baseconfig.json configs/
$ python3 normalize.py True
$ python3 create_dataset.py -f train_config -s 24000 -m dataset/multi_speaker_correspondence.txt
$ tensorboard --logdir logs --port 5000

2
docker_trainer/start_trainer.sh
View File

@ -1,7 +1,7 @@
#!/bin/bash
set -eu
DOCKER_IMAGE=dannadori/trainer:20230131_182050
DOCKER_IMAGE=dannadori/trainer:20230201_111603
docker run --gpus all --rm -ti \
-v `pwd`/trainer/dataset:/MMVC_Trainer/dataset \