PublicMirrors/voice-changer
1
0
Fork 0
mirror of https://github.com/w-okada/voice-changer.git synced 2025-01-23 21:45:00 +03:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #108 from w-okada/dev

Browse Source 
Dev
This commit is contained in:
w-okada 2022-12-09 10:52:42 +09:00 committed by GitHub
commit 755d70f515
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 150 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
VoiceChangerDemo.ipynb
View File

@ -5,7 +5,7 @@
"colab": {
"name": "VoiceChangerDemo",
"provenance": [],
"authorship_tag": "ABX9TyNpx+wMQQKflNKso1Aructr",
"authorship_tag": "ABX9TyMPAcI+ph7BN+Jg9dRQcidO",
"include_colab_link": true
},
"kernelspec": {
@ -74,15 +74,15 @@
"base_uri": "https://localhost:8080/"
},
"id": "vV1t7PBRm-o6",
"outputId": "76db7bf4-f28a-4049-833c-a9f17c1b5472"
"outputId": "1a01f054-42ef-4408-e6e5-36ae76fed751"
},
"execution_count": null,
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Sat Dec 3 10:47:24 2022 \n",
"Fri Dec 9 01:43:38 2022 \n",
"+-----------------------------------------------------------------------------+\n",
"| NVIDIA-SMI 460.32.03 Driver Version: 460.32.03 CUDA Version: 11.2 |\n",
"|-------------------------------+----------------------+----------------------+\n",
@ -91,7 +91,7 @@
"| | | MIG M. |\n",
"|===============================+======================+======================|\n",
"| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |\n",
"| N/A 51C P0 25W / 70W | 0MiB / 15109MiB | 0% Default |\n",
"| N/A 62C P0 29W / 70W | 0MiB / 15109MiB | 0% Default |\n",
"| | | N/A |\n",
"+-------------------------------+----------------------+----------------------+\n",
" \n",
@ -129,18 +129,18 @@
"metadata": {
"id": "nSXATMWYb4Ik"
},
"execution_count": null,
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2wxD-gRSMU5R",
"outputId": "ff4560ce-c04a-4fe8-bec3-3b93dfdd77ee"
"outputId": "0b649d6a-933e-45ab-e5a5-e024e8484936"
},
"outputs": [
{
@ -172,7 +172,7 @@
"source": [
"# (3) リポジトリのクローン\n",
"!git clone --depth 1 https://github.com/isletennos/MMVC_Trainer.git -b v1.3.1.5 /MMVC_Trainer\n",
"!git clone --depth 1 https://github.com/w-okada/voice-changer.git\n",
"!git clone --depth 1 https://github.com/w-okada/voice-changer.git -b ver_1.1\n",
"%cd /MMVC_Trainer/monotonic_align \n",
"!cythonize -3 -i core.pyx &> /dev/null\n",
"!mv core.cpython-*.so monotonic_align &> /dev/null\n",
@ -183,9 +183,9 @@
"base_uri": "https://localhost:8080/"
},
"id": "86wTFmqsNMnD",
"outputId": "35bad20a-b0a8-44c9-a072-10e11a199c50"
"outputId": "3f20280c-a9fd-48e7-afb1-0c598d7d4b6a"
},
"execution_count": null,
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
@ -196,15 +196,26 @@
"remote: Counting objects: 100% (917/917), done.\u001b[K\n",
"remote: Compressing objects: 100% (828/828), done.\u001b[K\n",
"remote: Total 917 (delta 3), reused 889 (delta 0), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (917/917), 53.02 MiB | 20.41 MiB/s, done.\n",
"Receiving objects: 100% (917/917), 53.02 MiB | 17.29 MiB/s, done.\n",
"Resolving deltas: 100% (3/3), done.\n",
"Cloning into 'voice-changer'...\n",
"remote: Enumerating objects: 108, done.\u001b[K\n",
"remote: Counting objects: 100% (108/108), done.\u001b[K\n",
"remote: Compressing objects: 100% (94/94), done.\u001b[K\n",
"remote: Total 108 (delta 15), reused 75 (delta 3), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (108/108), 18.79 MiB | 15.05 MiB/s, done.\n",
"remote: Enumerating objects: 109, done.\u001b[K\n",
"remote: Counting objects: 100% (109/109), done.\u001b[K\n",
"remote: Compressing objects: 100% (95/95), done.\u001b[K\n",
"remote: Total 109 (delta 15), reused 80 (delta 3), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (109/109), 18.79 MiB | 5.05 MiB/s, done.\n",
"Resolving deltas: 100% (15/15), done.\n",
"Note: checking out 'a5afb4441eef9b0a3234c62532199b19a5583fff'.\n",
"\n",
"You are in 'detached HEAD' state. You can look around, make experimental\n",
"changes and commit them, and you can discard any commits you make in this\n",
"state without impacting any branches by performing another checkout.\n",
"\n",
"If you want to create a new branch to retain commits you create, you may\n",
"do so (now or later) by using -b with the checkout command again. Example:\n",
"\n",
" git checkout -b <new-branch-name>\n",
"\n",
"/MMVC_Trainer/monotonic_align\n",
"/content/voice-changer/demo\n"
]
@ -230,7 +241,7 @@
"metadata": {
"id": "Bn4kV8TgXp8i"
},
"execution_count": null,
"execution_count": 5,
"outputs": []
},
{
@ -244,9 +255,9 @@
"base_uri": "https://localhost:8080/"
},
"id": "pjxPsOOaXXTj",
"outputId": "0aaa53de-2a45-45c1-b0e6-cc6de98873fe"
"outputId": "c3e8fc4d-0f0b-4271-c586-614f60a7b0e2"
},
"execution_count": null,
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
@ -350,7 +361,7 @@
"metadata": {
"id": "LwZAAuqxX7yY"
},
"execution_count": null,
"execution_count": 7,
"outputs": []
},
{
@ -401,7 +412,7 @@
"metadata": {
"id": "iNOAB7zISI6J"
},
"execution_count": null,
"execution_count": 8,
"outputs": []
},
{
@ -415,9 +426,9 @@
"base_uri": "https://localhost:8080/"
},
"id": "chu06KpAjEK6",
"outputId": "c1f8ca20-23e3-42c0-9143-b44498e84bd2"
"outputId": "8c1c6d17-375f-48db-dae8-b9a214470cd2"
},
"execution_count": null,
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
@ -466,15 +477,15 @@
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "96886f3d-3f88-4392-df41-90514fe4b0bc"
"outputId": "6538f2bb-0861-410b-f56b-647501ad11ed"
},
"execution_count": null,
"execution_count": 11,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"https://3lddbr773py-496ff2e9c6d22116-11741-colab.googleusercontent.com/front/\n"
"https://cyjqzm0tywm-496ff2e9c6d22116-13295-colab.googleusercontent.com/front/\n"
]
}
]

43
VoiceChangerDemo_Simple.ipynb
View File

@ -4,7 +4,7 @@
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyOpH+SznNefZ9FA23BSII8H",
"authorship_tag": "ABX9TyPpCB12DbPiDkKwIKIH79Oz",
"include_colab_link": true
},
"kernelspec": {
@ -73,7 +73,7 @@
"base_uri": "https://localhost:8080/"
},
"id": "vV1t7PBRm-o6",
"outputId": "0cf7f0ea-116e-452d-b1fd-4e8febe9ac74"
"outputId": "7bf2b1b0-5836-46c5-a89b-961ec4eeb21a"
},
"execution_count": 1,
"outputs": [
@ -81,7 +81,7 @@
"output_type": "stream",
"name": "stdout",
"text": [
"Sun Dec 4 12:49:59 2022 \n",
"Fri Dec 9 01:49:10 2022 \n",
"+-----------------------------------------------------------------------------+\n",
"| NVIDIA-SMI 460.32.03 Driver Version: 460.32.03 CUDA Version: 11.2 |\n",
"|-------------------------------+----------------------+----------------------+\n",
@ -90,7 +90,7 @@
"| | | MIG M. |\n",
"|===============================+======================+======================|\n",
"| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |\n",
"| N/A 36C P0 24W / 70W | 0MiB / 15109MiB | 0% Default |\n",
"| N/A 65C P0 30W / 70W | 0MiB / 15109MiB | 5% Default |\n",
"| | | N/A |\n",
"+-------------------------------+----------------------+----------------------+\n",
" \n",
@ -120,7 +120,7 @@
"source": [
"# (2) リポジトリのクローン\n",
"!git clone --depth 1 https://github.com/isletennos/MMVC_Trainer.git -b v1.3.1.3 /MMVC_Trainer\n",
"!git clone --depth 1 https://github.com/w-okada/voice-changer.git\n",
"!git clone --depth 1 https://github.com/w-okada/voice-changer.git -b ver_1.1\n",
"%cd /MMVC_Trainer/monotonic_align \n",
"!cythonize -3 -i core.pyx &> /dev/null\n",
"!mv core.cpython-*.so monotonic_align &> /dev/null\n",
@ -133,7 +133,7 @@
"base_uri": "https://localhost:8080/"
},
"id": "86wTFmqsNMnD",
"outputId": "456953e7-9fbe-47ca-dbca-7d8522501ce4"
"outputId": "b53c42fd-7479-4d69-8c4b-05342c0621dd"
},
"execution_count": 2,
"outputs": [
@ -146,7 +146,7 @@
"remote: Counting objects: 100% (917/917), done.\u001b[K\n",
"remote: Compressing objects: 100% (828/828), done.\u001b[K\n",
"remote: Total 917 (delta 3), reused 888 (delta 0), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (917/917), 53.02 MiB | 16.70 MiB/s, done.\n",
"Receiving objects: 100% (917/917), 53.02 MiB | 15.23 MiB/s, done.\n",
"Resolving deltas: 100% (3/3), done.\n",
"Note: checking out '39723b3243e0265b8802e020e4d4d90a4b8b65ee'.\n",
"\n",
@ -160,12 +160,23 @@
" git checkout -b <new-branch-name>\n",
"\n",
"Cloning into 'voice-changer'...\n",
"remote: Enumerating objects: 108, done.\u001b[K\n",
"remote: Counting objects: 100% (108/108), done.\u001b[K\n",
"remote: Compressing objects: 100% (94/94), done.\u001b[K\n",
"remote: Total 108 (delta 15), reused 73 (delta 3), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (108/108), 18.79 MiB | 13.48 MiB/s, done.\n",
"remote: Enumerating objects: 109, done.\u001b[K\n",
"remote: Counting objects: 100% (109/109), done.\u001b[K\n",
"remote: Compressing objects: 100% (95/95), done.\u001b[K\n",
"remote: Total 109 (delta 15), reused 80 (delta 3), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (109/109), 18.79 MiB | 13.06 MiB/s, done.\n",
"Resolving deltas: 100% (15/15), done.\n",
"Note: checking out 'a5afb4441eef9b0a3234c62532199b19a5583fff'.\n",
"\n",
"You are in 'detached HEAD' state. You can look around, make experimental\n",
"changes and commit them, and you can discard any commits you make in this\n",
"state without impacting any branches by performing another checkout.\n",
"\n",
"If you want to create a new branch to retain commits you create, you may\n",
"do so (now or later) by using -b with the checkout command again. Example:\n",
"\n",
" git checkout -b <new-branch-name>\n",
"\n",
"/MMVC_Trainer/monotonic_align\n",
"/content/voice-changer/demo\n"
]
@ -262,9 +273,9 @@
"base_uri": "https://localhost:8080/"
},
"id": "chu06KpAjEK6",
"outputId": "99777466-97a4-409f-e4de-9aeacf8d177e"
"outputId": "5ad0f8a8-6f8d-41c3-dc26-deecf2f05963"
},
"execution_count": 7,
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
@ -308,7 +319,7 @@
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "60b631dd-65d3-4c40-89d3-27c98b3abd72"
"outputId": "926db86f-5480-46e4-ee1e-38cfe45291b1"
},
"execution_count": 6,
"outputs": [
@ -316,7 +327,7 @@
"output_type": "stream",
"name": "stdout",
"text": [
"https://lzi676etq7d-496ff2e9c6d22116-14933-colab.googleusercontent.com/front/\n"
"https://gwhi5m8xqcp-496ff2e9c6d22116-14299-colab.googleusercontent.com/front/\n"
]
}
]

76
docker/Dockerfile_arm64 Normal file
View File

@ -0,0 +1,76 @@
FROM dannadori/voice-changer-internal:20221114_095228 as front
# FROM debian:bullseye-slim as base
# ARG DEBIAN_FRONTEND=noninteractive
# RUN apt-get update
# RUN apt-get install -y python3-pip git
# RUN apt-get install -y espeak
# RUN apt-get install -y cmake
# RUN pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
# RUN pip install Cython==0.29.32
# RUN pip install numpy==1.22.4
# RUN pip install scipy==1.9.0
# RUN pip install librosa==0.9.2
# RUN pip install phonemizer==3.2.1
# RUN pip install Unidecode==1.3.4
# RUN pip install resampy==0.4.0
# RUN pip install tqdm==4.64.0
# RUN pip install retry==0.9.2
# RUN pip install psutil==5.9.1
# RUN pip install python-socketio==5.7.1
# RUN pip install matplotlib==3.5.3
# RUN pip install fastapi==0.85.0
# RUN pip install python-multipart==0.0.5
# RUN pip install uvicorn==0.18.3
# RUN pip install websockets==10.4
# RUN pip install pyOpenSSL==22.0.0
# RUN pip install pyopenjtalk==0.2.0
# RUN pip install tensorboard==2.10.0
FROM sonoisa/deep-learning-coding:pytorch1.12.0_tensorflow2.9.1
RUN apt-get update \
&& apt-get install -y python3-pip espeak gosu libsndfile1-dev\
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
### Copy local resource
COPY fine_model/G_180000.pth /MMVC_Trainer/fine_model/G_180000.pth
COPY fine_model/D_180000.pth /MMVC_Trainer/fine_model/D_180000.pth
### Copy from base
# COPY --from=base --chmod=777 /usr/local/lib/python3.9/dist-packages /usr/local/lib/python3.9/dist-packages
### Copy from frontend
##### MMVC Trainer
COPY --from=front --chmod=777 /MMVC_Trainer /MMVC_Trainer
RUN chmod 0777 /MMVC_Trainer
ADD /setup.sh /MMVC_Trainer/
ADD /exec.sh /MMVC_Trainer/
##### Voice changer Internal
COPY --from=front --chmod=777 /voice-changer-internal/frontend/dist /voice-changer-internal/frontend/dist
COPY --from=front --chmod=777 /voice-changer-internal/voice-change-service /voice-changer-internal/voice-change-service
RUN chmod 0777 /voice-changer-internal/voice-change-service
## 歴史的な経緯でsetup.shをMMVC_Trainerに置いているのでそこを起動時のWORKDIRにしている。
WORKDIR /MMVC_Trainer
# ##### Soft VC
# COPY --from=front /hubert /hubert
# COPY --from=front /acoustic-model /acoustic-model
# COPY --from=front /hifigan /hifigan
# COPY --from=front /models /models
ENTRYPOINT ["/bin/bash", "setup.sh"]
CMD [ "-h"]

2
package.json
View File

@ -5,10 +5,12 @@
"main": "index.js",
"scripts": {
"build:docker": "date +%Y%m%d%H%M%S > docker/dummy && DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile docker/ -t voice-changer",
"build:docker_arm64": "date +%Y%m%d%H%M%S > docker/dummy && DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile_arm64 docker/ -t voice-changer-arm64",
"copy:frontend":"docker run -v `pwd`/frontend/dist:/frontend/dist --entrypoint /bin/bash -ti voice-changer -c \"cp -r /voice-changer-internal/frontend/dist/* /frontend/dist\"",
"copy:backend":"docker run -v `pwd`/demo:/demo --entrypoint /bin/bash -ti voice-changer -c \"cp -r /voice-changer-internal/voice-change-service/* /demo/\"",
"create:demo":"run-p copy:frontend copy:backend",
"push:docker": "bash script/001_pushDocker.sh",
"push:docker_arm64": "bash script/002_pushDocker_arm64.sh",
"test": "echo \"Error: no test specified\" && exit 1"
},
"repository": {

7
script/002_pushDocker_arm64.sh Normal file
View File

@ -0,0 +1,7 @@
#!/bin/bash
data_tag=`date +%Y%m%d_%H%M%S`
docker login
docker tag voice-changer dannadori/voice-changer-arm64:$data_tag
docker push dannadori/voice-changer-arm64:$data_tag