1berry/wokada-voice-changer
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of github.com:w-okada/voice-changer

Browse Source
This commit is contained in:
wataru 2023-01-14 07:36:29 +09:00
commit bf7f58b958
2 changed files with 69 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

88
VoiceChangerDemo.ipynb
View File

@ -5,7 +5,7 @@
"colab": {
"name": "VoiceChangerDemo",
"provenance": [],
"authorship_tag": "ABX9TyNnL+Mf0eEFM/VMaQZTahNn",
"authorship_tag": "ABX9TyNLt+Tfa4/4CVhJBwv4JieA",
"include_colab_link": true
},
"kernelspec": {
@ -76,7 +76,7 @@
"id": "vV1t7PBRm-o6",
"outputId": "dd745d3a-5b96-488a-ae51-39c47ec47b34"
},
"execution_count": 1,
"execution_count": null,
"outputs": [
{
"output_type": "stream",
@ -135,18 +135,18 @@
"metadata": {
"id": "nSXATMWYb4Ik"
},
"execution_count": 2,
"execution_count": 1,
"outputs": []
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2wxD-gRSMU5R",
"outputId": "c78a92f6-6631-476d-e967-0b797336eefc"
"outputId": "691379e5-de2d-483d-bb0f-35df0ea589a6"
},
"outputs": [
{
@ -177,40 +177,40 @@
"cell_type": "code",
"source": [
"# (3) リポジトリのクローン\n",
"!git clone --depth 1 https://github.com/w-okada/voice-changer.git -b v.1.3.3\n",
"!git clone --depth 1 https://github.com/w-okada/voice-changer.git -b v.1.3.4\n",
"%cd voice-changer/server\n",
"!git clone --depth 1 https://github.com/isletennos/MMVC_Trainer.git -b v1.3.2.2\n",
"!cd MMVC_Trainer/monotonic_align/ && python setup.py build_ext --inplace && cd -"
"!git clone https://github.com/isletennos/MMVC_Client.git\n",
"!cd MMVC_Client && git checkout 04f3fec4fd82dea6657026ec4e1cd80fb29a415c && cd -"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "86wTFmqsNMnD",
"outputId": "2de377dc-b76e-428d-81ae-59bf1d72e1cc"
"outputId": "ce9469b2-c327-440f-bba0-43285e6ec813"
},
"execution_count": 4,
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'voice-changer'...\n",
"remote: Enumerating objects: 143, done.\u001b[K\n",
"remote: Counting objects: 100% (143/143), done.\u001b[K\n",
"remote: Compressing objects: 100% (128/128), done.\u001b[K\n",
"remote: Total 143 (delta 20), reused 62 (delta 5), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (143/143), 1.52 MiB | 4.29 MiB/s, done.\n",
"remote: Enumerating objects: 144, done.\u001b[K\n",
"remote: Counting objects: 100% (144/144), done.\u001b[K\n",
"remote: Compressing objects: 100% (129/129), done.\u001b[K\n",
"remote: Total 144 (delta 20), reused 62 (delta 5), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (144/144), 1.52 MiB | 3.76 MiB/s, done.\n",
"Resolving deltas: 100% (20/20), done.\n",
"/content/voice-changer/server\n",
"Cloning into 'MMVC_Trainer'...\n",
"remote: Enumerating objects: 920, done.\u001b[K\n",
"remote: Counting objects: 100% (920/920), done.\u001b[K\n",
"remote: Compressing objects: 100% (830/830), done.\u001b[K\n",
"remote: Total 920 (delta 4), reused 893 (delta 1), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (920/920), 53.04 MiB | 17.82 MiB/s, done.\n",
"Resolving deltas: 100% (4/4), done.\n",
"Note: checking out 'f17c8c57d1ab7512633e6c57521f1eef6851bd0e'.\n",
"Cloning into 'MMVC_Client'...\n",
"remote: Enumerating objects: 594, done.\u001b[K\n",
"remote: Counting objects: 100% (322/322), done.\u001b[K\n",
"remote: Compressing objects: 100% (114/114), done.\u001b[K\n",
"remote: Total 594 (delta 231), reused 263 (delta 205), pack-reused 272\u001b[K\n",
"Receiving objects: 100% (594/594), 776.40 KiB | 13.62 MiB/s, done.\n",
"Resolving deltas: 100% (352/352), done.\n",
"Note: checking out '04f3fec4fd82dea6657026ec4e1cd80fb29a415c'.\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",
@ -221,16 +221,7 @@
"\n",
" git checkout -b <new-branch-name>\n",
"\n",
"Compiling core.pyx because it changed.\n",
"[1/1] Cythonizing core.pyx\n",
"/usr/local/lib/python3.8/dist-packages/Cython/Compiler/Main.py:369: FutureWarning: Cython directive 'language_level' not set, using 2 for now (Py2). This will change in a later release! File: /content/voice-changer/server/MMVC_Trainer/monotonic_align/core.pyx\n",
" tree = Parsing.p_module(s, pxd, full_module_name)\n",
"running build_ext\n",
"building 'monotonic_align.core' extension\n",
"creating build\n",
"creating build/temp.linux-x86_64-3.8\n",
"x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fstack-protector-strong -Wformat -Werror=format-security -g -fwrapv -O2 -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.8/dist-packages/numpy/core/include -I/usr/include/python3.8 -c core.c -o build/temp.linux-x86_64-3.8/core.o\n",
"x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -g -fwrapv -O2 -Wl,-Bsymbolic-functions -g -fwrapv -O2 -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.8/core.o -o /content/voice-changer/server/MMVC_Trainer/monotonic_align/monotonic_align/core.cpython-38-x86_64-linux-gnu.so\n",
"HEAD is now at 04f3fec Merge pull request #30 from Mokuichi147/setupcheck\n",
"/content/voice-changer/server\n"
]
}
@ -251,22 +242,19 @@
"cell_type": "code",
"source": [
"# (5) 設定ファイルの確認\n",
"!apt-get install -y espeak libsndfile1-dev &> /dev/null\n",
"!pip install unidecode &> /dev/null\n",
"!pip install phonemizer &> /dev/null\n",
"!pip install retry &> /dev/null\n",
"!pip install python-socketio &> /dev/null\n",
"!apt-get install -y libsndfile1-dev &> /dev/null\n",
"!pip install fastapi &> /dev/null\n",
"!pip install pyOpenSSL &> /dev/null\n",
"!pip install python-multipart &> /dev/null\n",
"!pip install python-socketio &> /dev/null\n",
"!pip install uvicorn &> /dev/null\n",
"!pip install websockets &> /dev/null\n",
"!pip install pyOpenSSL &> /dev/null\n",
"!pip install onnxruntime-gpu &> /dev/null"
],
"metadata": {
"id": "LwZAAuqxX7yY"
},
"execution_count": 5,
"execution_count": 4,
"outputs": []
},
{
@ -324,7 +312,7 @@
"metadata": {
"id": "iNOAB7zISI6J"
},
"execution_count": 6,
"execution_count": 5,
"outputs": []
},
{
@ -338,7 +326,7 @@
"base_uri": "https://localhost:8080/"
},
"id": "chu06KpAjEK6",
"outputId": "789c20be-249a-4965-f052-e3be9be12e24"
"outputId": "294388a0-d072-4790-e106-5d980c1f9c5a"
},
"execution_count": 7,
"outputs": [
@ -346,16 +334,20 @@
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[32m Phase name:__main__\u001b[0m\n",
"\u001b[32m PHASE3:__main__\u001b[0m\n",
"VoiceChanger Initialized (GPU_NUM:1, mps_enabled:False)\n",
"INFO:root:Loaded checkpoint '/content/drive/MyDrive/VoiceChanger/G_326000.pth' (iteration 1136)\n",
"/usr/local/lib/python3.8/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py:54: UserWarning: Specified provider 'OpenVINOExecutionProvider' is not in available provider names.Available providers: 'TensorrtExecutionProvider, CUDAExecutionProvider, CPUExecutionProvider'\n",
" warnings.warn(\n",
"/usr/local/lib/python3.8/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py:54: UserWarning: Specified provider 'DmlExecutionProvider' is not in available provider names.Available providers: 'TensorrtExecutionProvider, CUDAExecutionProvider, CPUExecutionProvider'\n",
" warnings.warn(\n",
"\u001b[32m Phase name:__main__\u001b[0m\n",
"\u001b[32m PHASE3:__main__\u001b[0m\n",
"VoiceChanger Initialized (GPU_NUM:1, mps_enabled:False)\n",
"\u001b[32m PHASE1:__main__\u001b[0m\n",
"\u001b[17mStart MMVC SocketIO Server\u001b[0m\n",
"\u001b[34m CONFIG:/content/drive/MyDrive/VoiceChanger/config.json, MODEL:None ONNX_MODEL:/content/drive/MyDrive/VoiceChanger/G_326000.onnx\u001b[0m\n"
"\u001b[34m CONFIG:/content/drive/MyDrive/VoiceChanger/config.json, MODEL:/content/drive/MyDrive/VoiceChanger/G_326000.pth ONNX_MODEL:/content/drive/MyDrive/VoiceChanger/G_326000.onnx\u001b[0m\n",
"\u001b[32m Phase name:MMVCServerSIO\u001b[0m\n",
"\u001b[32m PHASE3:MMVCServerSIO\u001b[0m\n",
"INFO:root:Loaded checkpoint '/content/drive/MyDrive/VoiceChanger/G_326000.pth' (iteration 1136)\n"
]
}
]
@ -388,7 +380,7 @@
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "2a578717-b723-4ec8-bdef-7633f2a9915c"
"outputId": "88aed9a7-8189-4b2a-d362-2129a8202e20"
},
"execution_count": 8,
"outputs": [
@ -396,7 +388,7 @@
"output_type": "stream",
"name": "stdout",
"text": [
"https://uukwsuu2e7s-496ff2e9c6d22116-11527-colab.googleusercontent.com/front/?colab=true\n"
"https://nc8xeapxkxg-496ff2e9c6d22116-10128-colab.googleusercontent.com/front/?colab=true\n"
]
}
]

70
VoiceChangerDemo_Simple.ipynb
View File

@ -4,7 +4,7 @@
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyP+LenGtlXFGimgObzNvgqS",
"authorship_tag": "ABX9TyPil77mdDP/EcndzrT40C2K",
"include_colab_link": true
},
"kernelspec": {
@ -73,7 +73,7 @@
"base_uri": "https://localhost:8080/"
},
"id": "vV1t7PBRm-o6",
"outputId": "85aaa5ec-0fc9-4433-96f3-5086c17e5ba1"
"outputId": "0780c5df-36cf-4f84-9a63-3669212d2769"
},
"execution_count": 1,
"outputs": [
@ -81,7 +81,7 @@
"output_type": "stream",
"name": "stdout",
"text": [
"Thu Jan 12 14:48:08 2023 \n",
"Fri Jan 13 22:07:27 2023 \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 58C P8 10W / 70W | 0MiB / 15109MiB | 0% Default |\n",
"| N/A 40C P8 9W / 70W | 0MiB / 15109MiB | 0% Default |\n",
"| | | N/A |\n",
"+-------------------------------+----------------------+----------------------+\n",
" \n",
@ -119,17 +119,17 @@
"cell_type": "code",
"source": [
"# (2) リポジトリのクローン\n",
"!git clone --depth 1 https://github.com/w-okada/voice-changer.git -b v.1.3.3\n",
"!git clone --depth 1 https://github.com/w-okada/voice-changer.git -b v.1.3.4\n",
"%cd voice-changer/server\n",
"!git clone --depth 1 https://github.com/isletennos/MMVC_Trainer.git -b v1.3.2.2\n",
"!cd MMVC_Trainer/monotonic_align/ && python setup.py build_ext --inplace && cd -\n"
"!git clone https://github.com/isletennos/MMVC_Client.git\n",
"!cd MMVC_Client && git checkout 04f3fec4fd82dea6657026ec4e1cd80fb29a415c && cd -\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "86wTFmqsNMnD",
"outputId": "27ad5458-3aee-4a05-945a-5b66fd603a8d"
"outputId": "fd283f8e-48a9-4dcb-e017-8e125a5f6000"
},
"execution_count": 2,
"outputs": [
@ -138,21 +138,21 @@
"name": "stdout",
"text": [
"Cloning into 'voice-changer'...\n",
"remote: Enumerating objects: 143, done.\u001b[K\n",
"remote: Counting objects: 100% (143/143), done.\u001b[K\n",
"remote: Compressing objects: 100% (128/128), done.\u001b[K\n",
"remote: Total 143 (delta 20), reused 62 (delta 5), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (143/143), 1.52 MiB | 4.30 MiB/s, done.\n",
"remote: Enumerating objects: 144, done.\u001b[K\n",
"remote: Counting objects: 100% (144/144), done.\u001b[K\n",
"remote: Compressing objects: 100% (129/129), done.\u001b[K\n",
"remote: Total 144 (delta 20), reused 62 (delta 5), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (144/144), 1.52 MiB | 4.11 MiB/s, done.\n",
"Resolving deltas: 100% (20/20), done.\n",
"/content/voice-changer/server\n",
"Cloning into 'MMVC_Trainer'...\n",
"remote: Enumerating objects: 920, done.\u001b[K\n",
"remote: Counting objects: 100% (920/920), done.\u001b[K\n",
"remote: Compressing objects: 100% (830/830), done.\u001b[K\n",
"remote: Total 920 (delta 4), reused 893 (delta 1), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (920/920), 53.04 MiB | 17.33 MiB/s, done.\n",
"Resolving deltas: 100% (4/4), done.\n",
"Note: checking out 'f17c8c57d1ab7512633e6c57521f1eef6851bd0e'.\n",
"Cloning into 'MMVC_Client'...\n",
"remote: Enumerating objects: 594, done.\u001b[K\n",
"remote: Counting objects: 100% (320/320), done.\u001b[K\n",
"remote: Compressing objects: 100% (114/114), done.\u001b[K\n",
"remote: Total 594 (delta 229), reused 261 (delta 203), pack-reused 274\u001b[K\n",
"Receiving objects: 100% (594/594), 738.87 KiB | 23.83 MiB/s, done.\n",
"Resolving deltas: 100% (351/351), done.\n",
"Note: checking out '04f3fec4fd82dea6657026ec4e1cd80fb29a415c'.\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",
@ -163,16 +163,7 @@
"\n",
" git checkout -b <new-branch-name>\n",
"\n",
"Compiling core.pyx because it changed.\n",
"[1/1] Cythonizing core.pyx\n",
"/usr/local/lib/python3.8/dist-packages/Cython/Compiler/Main.py:369: FutureWarning: Cython directive 'language_level' not set, using 2 for now (Py2). This will change in a later release! File: /content/voice-changer/server/MMVC_Trainer/monotonic_align/core.pyx\n",
" tree = Parsing.p_module(s, pxd, full_module_name)\n",
"running build_ext\n",
"building 'monotonic_align.core' extension\n",
"creating build\n",
"creating build/temp.linux-x86_64-3.8\n",
"x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fstack-protector-strong -Wformat -Werror=format-security -g -fwrapv -O2 -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.8/dist-packages/numpy/core/include -I/usr/include/python3.8 -c core.c -o build/temp.linux-x86_64-3.8/core.o\n",
"x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -g -fwrapv -O2 -Wl,-Bsymbolic-functions -g -fwrapv -O2 -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.8/core.o -o /content/voice-changer/server/MMVC_Trainer/monotonic_align/monotonic_align/core.cpython-38-x86_64-linux-gnu.so\n",
"HEAD is now at 04f3fec Merge pull request #30 from Mokuichi147/setupcheck\n",
"/content/voice-changer/server\n"
]
}
@ -194,16 +185,13 @@
"source": [
"# (3) 設定ファイルの確認\n",
"!apt-get install -y libsndfile1-dev &> /dev/null\n",
"!pip install unidecode &> /dev/null\n",
"!pip install phonemizer &> /dev/null\n",
"!pip install retry &> /dev/null\n",
"!pip install python-socketio &> /dev/null\n",
"!pip install fastapi &> /dev/null\n",
"!pip install pyOpenSSL &> /dev/null\n",
"!pip install python-multipart &> /dev/null\n",
"!pip install python-socketio &> /dev/null\n",
"!pip install uvicorn &> /dev/null\n",
"!pip install websockets &> /dev/null\n",
"!pip install pyOpenSSL &> /dev/null\n",
"!pip install onnxruntime-gpu &> /dev/null"
"!pip install onnxruntime-gpu &> /dev/null\n"
],
"metadata": {
"id": "LwZAAuqxX7yY"
@ -268,7 +256,7 @@
"base_uri": "https://localhost:8080/"
},
"id": "chu06KpAjEK6",
"outputId": "a4c8aea1-4193-4bb2-c128-3ed6d55e0270"
"outputId": "e8fa0415-b475-4fdf-ab49-3c363e3c2308"
},
"execution_count": 5,
"outputs": [
@ -313,7 +301,7 @@
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "349c76f5-c039-46e3-e73b-7582e21e2f23"
"outputId": "0de89da0-9ce9-4cc0-8070-166441a06fb7"
},
"execution_count": 6,
"outputs": [
@ -321,7 +309,7 @@
"output_type": "stream",
"name": "stdout",
"text": [
"https://pedza0b09p-496ff2e9c6d22116-12113-colab.googleusercontent.com/front/?colab=true\n"
"https://v8lm07nxaxe-496ff2e9c6d22116-10766-colab.googleusercontent.com/front/?colab=true\n"
]
}
]
@ -332,7 +320,7 @@
"metadata": {
"id": "axkt5BjhoiPV"
},
"execution_count": 6,
"execution_count": null,
"outputs": []
}
]