diff --git a/VoiceChangerDemo_Simple.ipynb b/VoiceChangerDemo_Simple.ipynb index 00fa7586..afd6112f 100644 --- a/VoiceChangerDemo_Simple.ipynb +++ b/VoiceChangerDemo_Simple.ipynb @@ -5,7 +5,7 @@ "colab": { "provenance": [], "collapsed_sections": [], - "authorship_tag": "ABX9TyN7lDdQ3iB8T1SI4BKFzkWz", + "authorship_tag": "ABX9TyMeMGMfscotyaoFPcXG8qRY", "include_colab_link": true }, "kernelspec": { @@ -74,15 +74,15 @@ "base_uri": "https://localhost:8080/" }, "id": "vV1t7PBRm-o6", - "outputId": "2ab5d79e-0fe1-4e48-9fb4-8a61399e0b60" + "outputId": "8e212991-8ca0-45bc-c632-40a707e9668e" }, - "execution_count": null, + "execution_count": 1, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - "Sun Oct 30 10:03:39 2022 \n", + "Thu Nov 3 21:54:01 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 35C P8 9W / 70W | 0MiB / 15109MiB | 0% Default |\n", + "| N/A 42C P0 25W / 70W | 0MiB / 15109MiB | 0% Default |\n", "| | | N/A |\n", "+-------------------------------+----------------------+----------------------+\n", " \n", @@ -106,57 +106,6 @@ } ] }, - { - "cell_type": "markdown", - "source": [ - "# 使用するモデルとコンフィグファイルの指定\n", - "\n", - "使用するトレーニング済みのモデルと、トレーニングで使用したコンフィグファイルのパスを指定してください。\n", - "\n", - "多くの場合はGoogle Driveに格納されているファイルを使用すると思います。その場合は、下の(2-2)のセルを実行してドライブをマウントしてください" - ], - "metadata": { - "id": "mHvGrgaWnIPA" - } - }, - { - "cell_type": "code", - "source": [ - "# # (2-1) 使用するモデルとコンフィグファイルの指定\n", - "# CONFIG=\"/content/drive/MyDrive/VoiceChanger/config.json\"\n", - "# MODEL=\"/content/drive/MyDrive/VoiceChanger/G_326000.pth\"" - ], - "metadata": { - "id": "nSXATMWYb4Ik" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "2wxD-gRSMU5R", - "outputId": "dabd982a-87c7-44d1-b9e8-986691190771" - }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Mounted at /content/drive\n" - ] - } - ], - "source": [ - "# # (2-2) Google Driveのマウント\n", - "# from google.colab import drive\n", - "# drive.mount('/content/drive')" - ] - }, { "cell_type": "markdown", "source": [ @@ -170,115 +119,51 @@ { "cell_type": "code", "source": [ - "# (3) リポジトリのクローン\n", + "# (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 -b dev\n", - "%cd voice-changer/demo/\n" + "%cd voice-changer/demo/\n", + "\n", + "!cp ../template/setting_mmvc_colab.json ../frontend/dist/assets/setting.json" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "86wTFmqsNMnD", - "outputId": "a52d5b0e-826e-445d-cd3a-4a42cbd52212" + "outputId": "a269932d-20e1-4fa0-ce86-00d231d169bd" }, - "execution_count": 36, + "execution_count": 2, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - "fatal: destination path '/MMVC_Trainer' already exists and is not an empty directory.\n", + "Cloning into '/MMVC_Trainer'...\n", + "remote: Enumerating objects: 917, done.\u001b[K\n", + "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 | 16.78 MiB/s, done.\n", + "Resolving deltas: 100% (3/3), done.\n", + "Note: checking out '39723b3243e0265b8802e020e4d4d90a4b8b65ee'.\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 \n", + "\n", "Cloning into 'voice-changer'...\n", - "remote: Enumerating objects: 88, done.\u001b[K\n", - "remote: Counting objects: 100% (88/88), done.\u001b[K\n", - "remote: Compressing objects: 100% (74/74), done.\u001b[K\n", - "remote: Total 88 (delta 14), reused 57 (delta 6), pack-reused 0\u001b[K\n", - "Unpacking objects: 100% (88/88), done.\n", - "/content/voice-changer/demo/voice-changer/demo/voice-changer/demo/voice-changer/demo/voice-changer/demo\n" - ] - } - ] - }, - { - "cell_type": "markdown", - "source": [ - "# ファイルの配置\n", - "アプリケーションの挙動を記した設定ファイルをコピーします(4-1)。(4-2)はコピーした設定ファイルを表示しています。もしかしたらうまく動かないときに役立つかもしれません。" - ], - "metadata": { - "id": "jmDY8W_fnuSi" - } - }, - { - "cell_type": "code", - "source": [ - "# (4-1) 設定ファイルの配置\n", - "!cp ../template/setting_mmvc_colab.json ../frontend/dist/assets/setting.json\n" - ], - "metadata": { - "id": "Bn4kV8TgXp8i" - }, - "execution_count": 37, - "outputs": [] - }, - { - "cell_type": "code", - "source": [ - "# (4-2) 設定ファイルの確認\n", - "!cat ../frontend/dist/assets/setting.json\n" - ], - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "pjxPsOOaXXTj", - "outputId": "425a36dd-fbdc-4f55-825e-a2c7026f2aab" - }, - "execution_count": 38, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "{\n", - " \"app_title\": \"voice-changer\",\n", - " \"majar_mode\": \"colab\",\n", - " \"voice_changer_server_url\": \"/test\",\n", - " \"sample_rate\": 48000,\n", - " \"buffer_size\": 1024,\n", - " \"prefix_chunk_size\": 36,\n", - " \"chunk_size\": 36,\n", - " \"speaker_ids\": [100, 107, 101, 102, 103],\n", - " \"speaker_names\": [\"ずんだもん\", \"user\", \"そら\", \"めたん\", \"つむぎ\"],\n", - " \"src_id\": 107,\n", - " \"dst_id\": 100,\n", - " \"vf_enable\": true,\n", - " \"voice_changer_mode\": \"realtime\",\n", - " \"gpu\": 0,\n", - " \"available_gpus\": [-1, 0, 1, 2, 3, 4],\n", - " \"avatar\": {\n", - " \"enable_avatar\": true, \n", - " \"motion_capture_face\": true,\n", - " \"motion_capture_upperbody\": true,\n", - " \"lip_overwrite_with_voice\": true,\n", - " \"avatar_url\": \"./assets/vrm/zundamon/zundamon.vrm\",\n", - " \"backgournd_image_url\": \"./assets/images/bg_natural_sougen.jpg\",\n", - " \"background_color\": \"#0000dd\",\n", - " \"chroma_key\": \"#0000dd\",\n", - " \"avatar_canvas_size\": [1280, 720],\n", - " \"screen_canvas_size\": [1280, 720]\n", - " },\n", - " \"advance\": {\n", - " \"avatar_draw_skip_rate\": 3,\n", - " \"screen_draw_skip_rate\": 3,\n", - " \"visualizer_draw_skip_rate\": 3,\n", - " \"cross_fade_lower_value\": 0.1,\n", - " \"cross_fade_offset_rate\": 0.3,\n", - " \"cross_fade_end_rate\": 0.6,\n", - " \"cross_fade_type\": 2\n", - " }\n", - "}\n" + "remote: Enumerating objects: 91, done.\u001b[K\n", + "remote: Counting objects: 100% (91/91), done.\u001b[K\n", + "remote: Compressing objects: 100% (79/79), done.\u001b[K\n", + "remote: Total 91 (delta 12), reused 55 (delta 4), pack-reused 0\u001b[K\n", + "Unpacking objects: 100% (91/91), done.\n", + "/content/voice-changer/demo\n" ] } ] @@ -297,7 +182,7 @@ { "cell_type": "code", "source": [ - "# (5) 設定ファイルの確認\n", + "# (3) 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", @@ -312,7 +197,7 @@ "metadata": { "id": "LwZAAuqxX7yY" }, - "execution_count": 44, + "execution_count": 3, "outputs": [] }, { @@ -320,14 +205,12 @@ "source": [ "# サーバの起動\n", "\n", - "サーバを起動します。(6-1)\n", + "サーバを起動します。(4-1)\n", "\n", - "サーバの起動状況を確認します。(6-2) \n", + "サーバの起動状況を確認します。(4-2) \n", "\n", "このセルは繰り返し実行することになるのでCtrl+Retでセルを実行してください。\n", "\n", - "アクセスできるようになるまで、１～２分かかるようです。コーヒーでも飲みに行きましょう。\n", - "\n", "下記のようなテキストが表示されたら起動完了です。\n", "\n", "**`DEBUG:asyncio:Using selector: EpollSelector`**\n", @@ -349,7 +232,7 @@ { "cell_type": "code", "source": [ - "# (6-1) サーバの起動\n", + "# (4-1) サーバの起動\n", "import random\n", "PORT = 10000 + random.randint(1, 9999)\n", "LOG_FILE = f\"LOG_FILE_{PORT}\"\n", @@ -358,27 +241,16 @@ "#print(f\"PORT:{PORT}, LOG_FILE:{LOG_FILE}\")" ], "metadata": { - "id": "G-nMdPxEW1rc", - "outputId": "ed5fc2d9-f1c5-4aa3-df8d-e306de2e2a30", - "colab": { - "base_uri": "https://localhost:8080/" - } + "id": "G-nMdPxEW1rc" }, - "execution_count": 40, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "PORT:19751, LOG_FILE:LOG_FILE_19751\n" - ] - } - ] + "execution_count": 4, + "outputs": [] }, { "cell_type": "code", "source": [ - "# (6-2) サーバの起動確認 (Ctrl+Retで実行)\n", + "# (4-2) サーバの起動確認\n", + "!sleep 5\n", "!tail -20 {LOG_FILE}" ], "metadata": { @@ -386,9 +258,9 @@ "base_uri": "https://localhost:8080/" }, "id": "chu06KpAjEK6", - "outputId": "e6b67606-1279-49aa-e276-4e2bb83284c1" + "outputId": "a1b039dc-8f47-44f4-fb02-be29f26468fd" }, - "execution_count": 45, + "execution_count": 7, "outputs": [ { "output_type": "stream", @@ -399,12 +271,7 @@ "\u001b[32m PHASE1:__main__\u001b[0m\n", "\u001b[17mStart MMVC SocketIO Server\u001b[0m\n", "\u001b[34m CONFIG:None, MODEL:None\u001b[0m\n", - "DEBUG:asyncio:Using selector: EpollSelector\n", - "\u001b[32m Phase name:MMVCServerSIO\u001b[0m\n", - "\u001b[32m PHASE3:MMVCServerSIO\u001b[0m\n", - "File saved to: G_326000.pth\n", - "Load: config.json, G_326000.pth\n", - "INFO:root:Loaded checkpoint 'model_upload_dir/G_326000.pth' (iteration 1136)\n" + "DEBUG:asyncio:Using selector: EpollSelector\n" ] } ] @@ -426,7 +293,7 @@ { "cell_type": "code", "source": [ - "# (7) プロキシを起動\n", + "# (5) プロキシを起動\n", "from google.colab.output import eval_js\n", "proxy = eval_js( \"google.colab.kernel.proxyPort(\" + str(PORT) + \")\" )\n", "print(f\"{proxy}front/\")" @@ -437,15 +304,15 @@ "base_uri": "https://localhost:8080/", "height": 34 }, - "outputId": "bbc830e9-209a-4b71-891d-8cf78cf3077d" + "outputId": "37531763-2abd-49e4-d2b7-0a301b9923de" }, - "execution_count": 43, + "execution_count": 6, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ - "https://w6x1mbngbj-496ff2e9c6d22116-19751-colab.googleusercontent.com/front/\n" + "https://s1ib44uhknk-496ff2e9c6d22116-19907-colab.googleusercontent.com/front/\n" ] } ] @@ -456,7 +323,7 @@ "metadata": { "id": "axkt5BjhoiPV" }, - "execution_count": null, + "execution_count": 6, "outputs": [] } ] diff --git a/template/setting_mmvc_colab.json b/template/setting_mmvc_colab.json index 30f8a197..6f766a81 100644 --- a/template/setting_mmvc_colab.json +++ b/template/setting_mmvc_colab.json @@ -4,8 +4,8 @@ "voice_changer_server_url": "/test", "sample_rate": 48000, "buffer_size": 1024, - "prefix_chunk_size": 24, - "chunk_size": 24, + "prefix_chunk_size": 48, + "chunk_size": 48, "speakers": [ { "id": 100,