Upload 2 files

Applio_NoUI.ipynb

@@ -0,0 +1,507 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0pKllbPyK_BC"
+      },
+      "source": [
+        "## **Applio NoUI**\n",
+        "A simple, high-quality voice conversion tool focused on ease of use and performance.\n",
+        "\n",
+        "[Support](https://discord.gg/urxFjYmYYh) — [GitHub](https://github.com/IAHispano/Applio) — [Terms of Use](https://github.com/IAHispano/Applio/blob/main/TERMS_OF_USE.md)\n",
+        "\n",
+        "<br>\n",
+        "\n",
+        "---\n",
+        "\n",
+        "<br>\n",
+        "\n",
+        "#### **Acknowledgments**\n",
+        "\n",
+        "To all external collaborators for their special help in the following areas: Hina (Encryption method), Poopmaster (Extra section), Shirou (UV installer),  Kit Lemonfoot (NoUI inspiration)\n",
+        "\n",
+        "#### **Disclaimer**\n",
+        "By using Applio, you agree to comply with ethical and legal standards, respect intellectual property and privacy rights, avoid harmful or prohibited uses, and accept full responsibility for any outcomes, while Applio disclaims liability and reserves the right to amend these terms."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ymMCTSD6m8qV"
+      },
+      "source": [
+        "### **Install Applio**\n",
+        "If the runtime restarts, re-run the installation steps."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "yFhAeKGOp9aa"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Mount Google Drive\n",
+        "from google.colab import drive\n",
+        "\n",
+        "drive.mount(\"/content/drive\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "CAXW55BQm0PP"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Setup runtime environment\n",
+        "from multiprocessing import cpu_count\n",
+        "cpu_cores = cpu_count()\n",
+        "post_process = False\n",
+        "hop_length = 128 # Common default value for hop_length, added for consistency across cells\n",
+        "\n",
+        "!git config --global advice.detachedHead false\n",
+        "!git clone https://github.com/IAHispano/Applio --branch 3.2.9 --single-branch\n",
+        "%cd /content/Applio\n",
+        "!sudo update-alternatives --set python3 /usr/bin/python3.10\n",
+        "!curl -LsSf https://astral.sh/uv/install.sh | sh\n",
+        "\n",
+        "print(\"Installing requirements...\")\n",
+        "!uv pip install -q -r requirements.txt\n",
+        "print(\"Finished installing requirements!\")\n",
+        "!python core.py \"prerequisites\" --models \"True\" --pretraineds_hifigan \"True\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# @title Unduh File Model\n",
+        "# @markdown Kode ini akan mengunduh file model yang diperlukan ke direktori `/content/`.\n",
+        "\n",
+        "import os\n",
+        "\n",
+        "# URL dan nama file\n",
+        "files_to_download = {\n",
+        "    \"D_GKv1_48k.pth\": \"https://huggingface.co/glickko/GK_pretrain/resolve/main/D_GKv1_48k.pth?download=true\",\n",
+        "    \"G_GKv1_48k.pth\": \"https://huggingface.co/glickko/GK_pretrain/resolve/main/G_GKv1_48k.pth?download=true\",\n",
+        "\n",
+        "}\n",
+        "\n",
+        "# Direktori tujuan\n",
+        "output_directory = \"/content\"\n",
+        "\n",
+        "# Proses pengunduhan\n",
+        "for filename, url in files_to_download.items():\n",
+        "    output_path = os.path.join(output_directory, filename)\n",
+        "    print(f\"Mengunduh {filename}...\")\n",
+        "    # Menggunakan wget untuk mengunduh file\n",
+        "    !wget -q --show-progress -O {output_path} \"{url}\"\n",
+        "    print(f\"Selesai! File disimpan di: {output_path}\\n\")\n",
+        "\n",
+        "print(\"🎉 Semua file telah berhasil diunduh.\")\n",
+        "\n",
+        "# Menampilkan isi folder /content untuk verifikasi\n",
+        "print(\"\\nIsi folder /content saat ini:\")\n",
+        "!ls -lh /content"
+      ],
+      "metadata": {
+        "id": "eYCTi9pE90fU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1QkabnLlF2KB"
+      },
+      "source": [
+        "### **Train**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# @title Setup model variables\n",
+        "model_name = \"\" # @param {type:\"string\"}\n",
+        "sample_rate = \"48k\"  # @param [\"32k\", \"40k\", \"48k\"] {allow-input: false}\n",
+        "sr = int(sample_rate.rstrip(\"k\")) * 1000"
+      ],
+      "metadata": {
+        "cellView": "form",
+        "id": "64V5TWxp05cn"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "oBzqm4JkGGa0"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Preprocess Dataset\n",
+        "from os import environ\n",
+        "environ['TF_CPP_MIN_LOG_LEVEL'] = '3'\n",
+        "dataset_path = \"\"  # @param {type:\"string\"}\n",
+        "\n",
+        "cut_preprocess = \"Simple\" # @param [\"Skip\",\"Simple\",\"Automatic\"]\n",
+        "chunk_len = 5 # @param {type:\"slider\", min:0.5, max:5.0, step:0.5}\n",
+        "overlap_len = 0.3 # @param {type:\"slider\", min:0, max:0.5, step:0.1}\n",
+        "process_effects = False # @param{type:\"boolean\"}\n",
+        "noise_reduction = False # @param{type:\"boolean\"}\n",
+        "noise_reduction_strength = 0.7 # @param {type:\"slider\", min:0.0, max:1.0, step:0.1}\n",
+        "\n",
+        "%cd /content/Applio\n",
+        "!python core.py preprocess --model_name \"{model_name}\" --dataset_path \"{dataset_path}\" --sample_rate \"{sr}\" --cpu_cores \"{cpu_cores}\" --cut_preprocess \"{cut_preprocess}\" --process_effects \"{process_effects}\" --noise_reduction \"{noise_reduction}\" --noise_reduction_strength \"{noise_reduction_strength}\" --chunk_len \"{chunk_len}\" --overlap_len \"{overlap_len}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "zWMiMYfRJTJv"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Extract Features\n",
+        "f0_method = \"rmvpe\"  # @param [\"crepe\", \"crepe-tiny\", \"rmvpe\"] {allow-input: false}\n",
+        "\n",
+        "sr = int(sample_rate.rstrip(\"k\")) * 1000\n",
+        "include_mutes = 2 # @param {type:\"slider\", min:0, max:10, step:1}\n",
+        "embedder_model = \"contentvec\" # @param [\"contentvec\", \"chinese-hubert-base\", \"japanese-hubert-base\", \"korean-hubert-base\", \"custom\"] {allow-input: false}\n",
+        "embedder_model_custom = \"\" # @param {type:\"string\"}\n",
+        "\n",
+        "%cd /content/Applio\n",
+        "!python core.py extract --model_name \"{model_name}\" --f0_method \"{f0_method}\" --hop_length \"{hop_length}\" --sample_rate \"{sr}\" --cpu_cores \"{cpu_cores}\" --gpu \"0\" --embedder_model \"{embedder_model}\" --embedder_model_custom \"{embedder_model_custom}\"  --include_mutes \"{include_mutes}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "bHLs5AT4Q1ck"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Generate index file\n",
+        "index_algorithm = \"Auto\"  # @param [\"Auto\", \"Faiss\", \"KMeans\"] {allow-input: false}\n",
+        "\n",
+        "%cd /content/Applio\n",
+        "!python core.py index --model_name \"{model_name}\" --index_algorithm \"{index_algorithm}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "TI6LLdIzKAIa"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Start Training\n",
+        "import threading\n",
+        "import time\n",
+        "import os\n",
+        "import shutil\n",
+        "import hashlib\n",
+        "import time\n",
+        "\n",
+        "LOGS_FOLDER = \"/content/Applio/logs/\"\n",
+        "GOOGLE_DRIVE_PATH = \"/content/drive/MyDrive/RVC_Backup\"\n",
+        "\n",
+        "\n",
+        "def import_google_drive_backup():\n",
+        "    print(\"Importing Google Drive backup...\")\n",
+        "    for root, dirs, files in os.walk(GOOGLE_DRIVE_PATH):\n",
+        "        for filename in files:\n",
+        "            filepath = os.path.join(root, filename)\n",
+        "            if os.path.isfile(filepath):\n",
+        "                backup_filepath = os.path.join(\n",
+        "                    LOGS_FOLDER, os.path.relpath(filepath, GOOGLE_DRIVE_PATH)\n",
+        "                )\n",
+        "                backup_folderpath = os.path.dirname(backup_filepath)\n",
+        "                if not os.path.exists(backup_folderpath):\n",
+        "                    os.makedirs(backup_folderpath)\n",
+        "                    print(f\"Created backup folder: {backup_folderpath}\", flush=True)\n",
+        "                shutil.copy2(filepath, backup_filepath)\n",
+        "                print(f\"Imported file from Google Drive backup: {filename}\")\n",
+        "    print(\"Google Drive backup import completed.\")\n",
+        "\n",
+        "\n",
+        "if \"autobackups\" not in globals():\n",
+        "    autobackups = False\n",
+        "# @markdown ### 💾 AutoBackup\n",
+        "cooldown = 15  # @param {type:\"slider\", min:0, max:100, step:0}\n",
+        "auto_backups = True  # @param{type:\"boolean\"}\n",
+        "def backup_files():\n",
+        "    print(\"\\nStarting backup loop...\")\n",
+        "    last_backup_timestamps_path = os.path.join(\n",
+        "        LOGS_FOLDER, \"last_backup_timestamps.txt\"\n",
+        "    )\n",
+        "    fully_updated = False\n",
+        "\n",
+        "    while True:\n",
+        "        try:\n",
+        "            updated_files = 0\n",
+        "            deleted_files = 0\n",
+        "            new_files = 0\n",
+        "            last_backup_timestamps = {}\n",
+        "\n",
+        "            try:\n",
+        "                with open(last_backup_timestamps_path, \"r\") as f:\n",
+        "                    last_backup_timestamps = dict(line.strip().split(\":\") for line in f)\n",
+        "            except FileNotFoundError:\n",
+        "                pass\n",
+        "\n",
+        "            for root, dirs, files in os.walk(LOGS_FOLDER):\n",
+        "                # Excluding \"zips\" and \"mute\" directories\n",
+        "                if \"zips\" in dirs:\n",
+        "                    dirs.remove(\"zips\")\n",
+        "                if \"mute\" in dirs:\n",
+        "                    dirs.remove(\"mute\")\n",
+        "\n",
+        "                for filename in files:\n",
+        "                    if filename != \"last_backup_timestamps.txt\":\n",
+        "                        filepath = os.path.join(root, filename)\n",
+        "                        if os.path.isfile(filepath):\n",
+        "                            backup_filepath = os.path.join(\n",
+        "                                GOOGLE_DRIVE_PATH,\n",
+        "                                os.path.relpath(filepath, LOGS_FOLDER),\n",
+        "                            )\n",
+        "                            backup_folderpath = os.path.dirname(backup_filepath)\n",
+        "                            if not os.path.exists(backup_folderpath):\n",
+        "                                os.makedirs(backup_folderpath)\n",
+        "                            last_backup_timestamp = last_backup_timestamps.get(filepath)\n",
+        "                            current_timestamp = os.path.getmtime(filepath)\n",
+        "                            if (\n",
+        "                                last_backup_timestamp is None\n",
+        "                                or float(last_backup_timestamp) < current_timestamp\n",
+        "                            ):\n",
+        "                                shutil.copy2(filepath, backup_filepath)\n",
+        "                                last_backup_timestamps[filepath] = str(current_timestamp)\n",
+        "                                if last_backup_timestamp is None:\n",
+        "                                    new_files += 1\n",
+        "                                else:\n",
+        "                                    updated_files += 1\n",
+        "\n",
+        "\n",
+        "            for filepath in list(last_backup_timestamps.keys()):\n",
+        "                if not os.path.exists(filepath):\n",
+        "                    backup_filepath = os.path.join(\n",
+        "                        GOOGLE_DRIVE_PATH, os.path.relpath(filepath, LOGS_FOLDER)\n",
+        "                    )\n",
+        "                    if os.path.exists(backup_filepath):\n",
+        "                        os.remove(backup_filepath)\n",
+        "                        deleted_files += 1\n",
+        "                    del last_backup_timestamps[filepath]\n",
+        "\n",
+        "\n",
+        "            if updated_files > 0 or deleted_files > 0 or new_files > 0:\n",
+        "                print(f\"Backup Complete: {new_files} new, {updated_files} updated, {deleted_files} deleted.\")\n",
+        "                fully_updated = False\n",
+        "            elif not fully_updated:\n",
+        "                print(\"Files are up to date.\")\n",
+        "                fully_updated = True\n",
+        "\n",
+        "            with open(last_backup_timestamps_path, \"w\") as f:\n",
+        "                for filepath, timestamp in last_backup_timestamps.items():\n",
+        "                    f.write(f\"{filepath}:{timestamp}\\n\")\n",
+        "\n",
+        "            time.sleep(cooldown if fully_updated else 0.1)\n",
+        "\n",
+        "\n",
+        "        except Exception as error:\n",
+        "            print(f\"An error occurred during backup: {error}\")\n",
+        "\n",
+        "\n",
+        "if autobackups:\n",
+        "    autobackups = False\n",
+        "    print(\"Autobackup Disabled\")\n",
+        "else:\n",
+        "    autobackups = True\n",
+        "    print(\"Autobackup Enabled\")\n",
+        "# @markdown ### ⚙️ Train Settings\n",
+        "total_epoch = 150  # @param {type:\"integer\"}\n",
+        "batch_size = 19  # @param {type:\"slider\", min:1, max:25, step:0}\n",
+        "gpu = 0\n",
+        "sr = int(sample_rate.rstrip(\"k\")) * 1000\n",
+        "pretrained = True  # @param{type:\"boolean\"}\n",
+        "cleanup = False  # @param{type:\"boolean\"}\n",
+        "cache_data_in_gpu = False  # @param{type:\"boolean\"}\n",
+        "vocoder = \"HiFi-GAN\" # @param [\"HiFi-GAN\"]\n",
+        "checkpointing = False\n",
+        "tensorboard = True  # @param{type:\"boolean\"}\n",
+        "# @markdown ### ➡️ Choose how many epochs your model will be stored\n",
+        "save_every_epoch = 10  # @param {type:\"slider\", min:1, max:100, step:0}\n",
+        "save_only_latest = True  # @param{type:\"boolean\"}\n",
+        "save_every_weights = True  # @param{type:\"boolean\"}\n",
+        "overtraining_detector = False  # @param{type:\"boolean\"}\n",
+        "overtraining_threshold = 50  # @param {type:\"slider\", min:1, max:100, step:0}\n",
+        "# @markdown ### ❓ Optional\n",
+        "# @markdown In case you select custom pretrained, you will have to download the pretraineds and enter the path of the pretraineds.\n",
+        "custom_pretrained = True  # @param{type:\"boolean\"}\n",
+        "g_pretrained_path = \"/content/G_GKv1_48k.pth\"  # @param {type:\"string\"}\n",
+        "d_pretrained_path = \"/content/D_GKv1_48k.pth\"  # @param {type:\"string\"}\n",
+        "\n",
+        "if \"pretrained\" not in globals():\n",
+        "    pretrained = True\n",
+        "\n",
+        "if \"custom_pretrained\" not in globals():\n",
+        "    custom_pretrained = False\n",
+        "\n",
+        "if \"g_pretrained_path\" not in globals():\n",
+        "    g_pretrained_path = \"Custom Path\"\n",
+        "\n",
+        "if \"d_pretrained_path\" not in globals():\n",
+        "    d_pretrained_path = \"Custom Path\"\n",
+        "\n",
+        "\n",
+        "def start_train():\n",
+        "    if tensorboard == True:\n",
+        "        %load_ext tensorboard\n",
+        "        %tensorboard --logdir /content/Applio/logs/\n",
+        "    %cd /content/Applio\n",
+        "    !python core.py train --model_name \"{model_name}\" --save_every_epoch \"{save_every_epoch}\" --save_only_latest \"{save_only_latest}\" --save_every_weights \"{save_every_weights}\" --total_epoch \"{total_epoch}\" --sample_rate \"{sr}\" --batch_size \"{batch_size}\" --gpu \"{gpu}\" --pretrained \"{pretrained}\" --custom_pretrained \"{custom_pretrained}\" --g_pretrained_path \"{g_pretrained_path}\" --d_pretrained_path \"{d_pretrained_path}\" --overtraining_detector \"{overtraining_detector}\" --overtraining_threshold \"{overtraining_threshold}\" --cleanup \"{cleanup}\" --cache_data_in_gpu \"{cache_data_in_gpu}\" --vocoder \"{vocoder}\" --checkpointing \"{checkpointing}\"\n",
+        "\n",
+        "\n",
+        "server_thread = threading.Thread(target=start_train)\n",
+        "server_thread.start()\n",
+        "\n",
+        "if auto_backups:\n",
+        "    backup_files()\n",
+        "else:\n",
+        "    while True:\n",
+        "        time.sleep(10)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "X_eU_SoiHIQg"
+      },
+      "source": [
+        "# @title Export model\n",
+        "from pathlib import Path\n",
+        "\n",
+        "export_for = \"training\" # @param [\"training\", \"inference\"] {allow-input: false}\n",
+        "\n",
+        "logs_folder = Path(f\"/content/Applio/logs/{model_name}/\")\n",
+        "if not (logs_folder.exists() and logs_folder.is_dir()):\n",
+        "    raise FileNotFoundError(f\"{model_name} model folder not found\")\n",
+        "\n",
+        "%cd {logs_folder}/..\n",
+        "if export_for == \"training\":\n",
+        "  !zip -r \"/content/{model_name}.zip\" \"{model_name}\"\n",
+        "else:\n",
+        "  # find latest trained weight file\n",
+        "  !ls -t \"{model_name}/{model_name}\"_*e_*s.pth | head -n 1 > /tmp/weight.txt\n",
+        "  weight_path = open(\"/tmp/weight.txt\", \"r\").read().strip()\n",
+        "  if weight_path == \"\":\n",
+        "    raise FileNotFoundError(\"Model has no weight file, please finish training first\")\n",
+        "  weight_name = Path(weight_path).name\n",
+        "  # command does not fail if index is missing, and i allow it\n",
+        "  !zip \"/content/{model_name}.zip\" \"{model_name}/{weight_name}\" \"{model_name}/{model_name}.index\"\n",
+        "\n",
+        "BACKUP_PATH = \"/content/drive/MyDrive/RVC_Backup/\"\n",
+        "if Path(\"/content/drive\").is_mount():\n",
+        "  !mkdir -p \"{BACKUP_PATH}\"\n",
+        "  !mv \"/content/{model_name}.zip\" \"{BACKUP_PATH}\" && echo \"Exported model as {BACKUP_PATH}{model_name}.zip\"\n",
+        "else:\n",
+        "  !echo \"Drive not mounted, exporting model as /content/{model_name}.zip\""
+      ],
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "OaKoymXsyEYN"
+      },
+      "source": [
+        "### **Resume training**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "d3KgLAYnyHkP"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Load a Backup\n",
+        "from google.colab import drive\n",
+        "import os\n",
+        "import shutil\n",
+        "\n",
+        "# @markdown Put the exact name you put as your Model Name in Applio.\n",
+        "modelname = \"My-Project\"  # @param {type:\"string\"}\n",
+        "source_path = \"/content/drive/MyDrive/RVC_Backup/\" + modelname\n",
+        "destination_path = \"/content/Applio/logs/\" + modelname\n",
+        "backup_timestamps_file = \"last_backup_timestamps.txt\"\n",
+        "if not os.path.exists(source_path):\n",
+        "    print(\n",
+        "        \"The model folder does not exist. Please verify the name is correct or check your Google Drive.\"\n",
+        "    )\n",
+        "else:\n",
+        "    time_ = os.path.join(\"/content/drive/MyDrive/RVC_Backup/\", backup_timestamps_file)\n",
+        "    time__ = os.path.join(\"/content/Applio/logs/\", backup_timestamps_file)\n",
+        "    if os.path.exists(time_):\n",
+        "        shutil.copy(time_, time__)\n",
+        "    shutil.copytree(source_path, destination_path)\n",
+        "    print(\"Model backup loaded successfully.\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "sc9DzvRCyJ2d"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Set training variables\n",
+        "# @markdown ### ➡️ Use the same as you did previously\n",
+        "model_name = \"Darwin\"  # @param {type:\"string\"}\n",
+        "sample_rate = \"40k\"  # @param [\"32k\", \"40k\", \"48k\"] {allow-input: false}\n",
+        "f0_method = \"rmvpe\"  # @param [\"crepe\", \"crepe-tiny\", \"rmvpe\"] {allow-input: false}\n",
+        "sr = int(sample_rate.rstrip(\"k\")) * 1000"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "collapsed_sections": [
+        "ymMCTSD6m8qV"
+      ],
+      "provenance": [],
+      "private_outputs": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

RVC_Datasets_Maker.ipynb

@@ -0,0 +1,399 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "gpuType": "T4"
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "accelerator": "GPU"
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "source": [
+        "#@title Mount Google Drive\n",
+        "from google.colab import drive\n",
+        "drive.mount('/content/drive')"
+      ],
+      "metadata": {
+        "id": "RkuSSLb7t39L",
+        "cellView": "form"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#@title  Parameters\n",
+        "#@markdown ### **1. General Settings**\n",
+        "project_name = \"\"  #@param {type:\"string\"}\n",
+        "mode = \"Splitting\"  #@param [\"Splitting\", \"Separate\"]\n",
+        "demucs_model = \"htdemucs\"  #@param [\"htdemucs\", \"demucs\", \"htdemucs_ft\", \"demucs_extra\"]\n",
+        "\n",
+        "#@markdown ---\n",
+        "#@markdown ### **2. Input Source**\n",
+        "dataset_source = \"Youtube\"  #@param [\"Youtube\", \"Drive\"]\n",
+        "#@markdown **If YouTube:** Provide one or more URLs, separated by commas.\n",
+        "youtube_urls = \"\" #@param {type:\"string\"}\n",
+        "#@markdown **If Drive:** Provide the full path to the FOLDER containing your audio files.\n",
+        "google_drive_folder_path = \"\" #@param {type:\"string\"}\n",
+        "\n",
+        "#@markdown ---\n",
+        "#@markdown ### **3. Processing Settings**\n",
+        "#@markdown **YouTube Trimming (Optional):** Use HH:MM:SS format.\n",
+        "start_time = \"\" #@param {type:\"string\"}\n",
+        "end_time = \"\" #@param {type:\"string\"}\n",
+        "#@markdown **Long Audio Handling:** Split audio longer than this duration before processing with Demucs.\n",
+        "chunk_duration_in_minutes = \"30 minutes\" #@param [\"10 minutes\", \"15 minutes\", \"20 minutes\", \"30 minutes\", \"45 minutes\", \"60 minutes\"]\n",
+        "\n",
+        "#@markdown ---\n",
+        "#@markdown ### **4. Output Settings**\n",
+        "#@markdown Sample rate for the output files. `0` uses the original sample rate.\n",
+        "output_sample_rate = \"48000\"  #@param [\"0\", \"8000\", \"16000\", \"22050\", \"32000\", \"44100\", \"48000\"]\n",
+        "output_format = \"mp3\" #@param [\"wav\", \"mp3\"]\n",
+        "\n",
+        "# --- Process Parameters for the next cell ---\n",
+        "chunk_duration_map = {\n",
+        "    \"10 minutes\": 600,\n",
+        "    \"15 minutes\": 900,\n",
+        "    \"20 minutes\": 1200,\n",
+        "    \"30 minutes\": 1800,\n",
+        "    \"45 minutes\": 2700,\n",
+        "    \"60 minutes\": 3600\n",
+        "}\n",
+        "chunk_duration = chunk_duration_map[chunk_duration_in_minutes]\n",
+        "output_sr = int(output_sample_rate)\n",
+        "\n",
+        "# Map new variables to old names for compatibility with the processing script\n",
+        "url = youtube_urls\n",
+        "drive_path = google_drive_folder_path\n",
+        "dataset = dataset_source"
+      ],
+      "metadata": {
+        "id": "23UmiGqUt_0a",
+        "cellView": "form"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#@title Process Dataset\n",
+        "import os\n",
+        "import subprocess\n",
+        "import glob\n",
+        "import shutil\n",
+        "\n",
+        "print(\"Memulai proses...\\n\")\n",
+        "\n",
+        "# Pastikan runtime Colab menggunakan GPU\n",
+        "print(\"GPU Info:\")\n",
+        "!nvidia-smi\n",
+        "print(\"\\n\")\n",
+        "\n",
+        "# --- Helper Functions ---\n",
+        "def get_duration(file_path):\n",
+        "    try:\n",
+        "        result = subprocess.run(\n",
+        "            [\"ffprobe\", \"-v\", \"error\", \"-show_entries\", \"format=duration\",\n",
+        "             \"-of\", \"default=noprint_wrappers=1:nokey=1\", file_path],\n",
+        "            stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)\n",
+        "        return float(result.stdout.strip())\n",
+        "    except Exception as e:\n",
+        "        print(f\"Gagal mendapatkan durasi audio untuk {file_path}: {e}\")\n",
+        "        return None\n",
+        "\n",
+        "def run_command(command):\n",
+        "    result = subprocess.run(command, shell=True, capture_output=True, text=True)\n",
+        "    if result.stdout:\n",
+        "        print(result.stdout)\n",
+        "    if result.stderr:\n",
+        "        print(result.stderr)\n",
+        "\n",
+        "# --- Input Validation ---\n",
+        "if not project_name:\n",
+        "    raise ValueError(\"Error: Project Name tidak boleh kosong!\")\n",
+        "if dataset == \"Youtube\" and not url:\n",
+        "    raise ValueError(\"Error: URL tidak boleh kosong untuk dataset Youtube!\")\n",
+        "if dataset == \"Drive\" and not drive_path:\n",
+        "    raise ValueError(\"Error: Drive Path tidak boleh kosong untuk dataset Drive!\")\n",
+        "\n",
+        "# --- Install Dependencies ---\n",
+        "print(\"Menginstal/memperbarui dependensi (yt_dlp, ffmpeg, demucs, librosa)...\")\n",
+        "run_command(\"python3 -m pip install --upgrade yt_dlp ffmpeg-python demucs librosa soundfile --quiet\")\n",
+        "\n",
+        "# === STEP 1: Gather All Audio Sources ===\n",
+        "source_audio_paths = []\n",
+        "temp_download_folder = \"temp_audio_downloads\"\n",
+        "os.makedirs(temp_download_folder, exist_ok=True)\n",
+        "\n",
+        "if dataset == \"Youtube\":\n",
+        "    urls = [u.strip() for u in url.split(',') if u.strip()]\n",
+        "    print(f\"Ditemukan {len(urls)} URL YouTube untuk diproses.\")\n",
+        "    import yt_dlp\n",
+        "    for i, u in enumerate(urls):\n",
+        "        print(f\"\\nDownloading audio ({i+1}/{len(urls)}) dari: {u}\")\n",
+        "        try:\n",
+        "            ydl_opts = {\n",
+        "                'format': 'bestaudio/best',\n",
+        "                'postprocessors': [{'key': 'FFmpegExtractAudio', 'preferredcodec': 'wav'}],\n",
+        "                'outtmpl': f'{temp_download_folder}/{project_name}_yt_{i+1}.%(ext)s'\n",
+        "            }\n",
+        "            with yt_dlp.YoutubeDL(ydl_opts) as ydl:\n",
+        "                ydl.download([u])\n",
+        "            downloaded_file = os.path.abspath(f\"{temp_download_folder}/{project_name}_yt_{i+1}.wav\")\n",
+        "\n",
+        "            # Trimming Logic\n",
+        "            if start_time and end_time:\n",
+        "                print(f\"Melakukan trimming audio dari {start_time} ke {end_time}...\")\n",
+        "                trimmed_file = os.path.abspath(f\"{temp_download_folder}/{project_name}_yt_{i+1}_trimmed.wav\")\n",
+        "                trim_cmd = f'ffmpeg -i \"{downloaded_file}\" -ss {start_time} -to {end_time} -c copy \"{trimmed_file}\"'\n",
+        "                run_command(trim_cmd)\n",
+        "                if os.path.exists(trimmed_file):\n",
+        "                    source_audio_paths.append(trimmed_file)\n",
+        "                else:\n",
+        "                    print(f\"Warning: Gagal melakukan trimming, file akan diproses penuh.\")\n",
+        "                    source_audio_paths.append(downloaded_file)\n",
+        "            else:\n",
+        "                source_audio_paths.append(downloaded_file)\n",
+        "        except Exception as e:\n",
+        "            print(f\"Gagal mendownload atau memproses URL {u}: {e}\")\n",
+        "elif dataset == \"Drive\":\n",
+        "    print(f\"Mencari file audio di folder: {drive_path}\")\n",
+        "    allowed_extensions = [\"*.wav\", \"*.mp3\", \"*.flac\", \"*.m4a\"]\n",
+        "    for ext in allowed_extensions:\n",
+        "        source_audio_paths.extend(glob.glob(os.path.join(drive_path, ext)))\n",
+        "    print(f\"Ditemukan {len(source_audio_paths)} file audio.\")\n",
+        "\n",
+        "if not source_audio_paths:\n",
+        "    raise Exception(\"Tidak ada file audio sumber yang ditemukan. Hentikan proses.\")\n",
+        "\n",
+        "# === STEP 2: Process Each Audio Source with Demucs ===\n",
+        "all_vocals_paths = []\n",
+        "for idx, audio_input in enumerate(source_audio_paths):\n",
+        "    current_audio_name = os.path.splitext(os.path.basename(audio_input))[0]\n",
+        "    print(f\"\\n--- Memproses file {idx+1}/{len(source_audio_paths)}: {current_audio_name} ---\")\n",
+        "    duration = get_duration(audio_input)\n",
+        "    if duration is None:\n",
+        "        print(f\"Melewatkan file karena tidak bisa mendapatkan durasi.\")\n",
+        "        continue\n",
+        "    print(f\"Durasi audio: {duration:.0f} detik.\")\n",
+        "\n",
+        "    if duration > chunk_duration:\n",
+        "        print(f\"Audio lebih panjang dari {chunk_duration} detik. Melakukan splitting audio menjadi beberapa chunk...\")\n",
+        "        chunk_folder = f\"chunks/{current_audio_name}\"\n",
+        "        os.makedirs(chunk_folder, exist_ok=True)\n",
+        "        split_cmd = f'ffmpeg -hide_banner -loglevel error -i \"{audio_input}\" -f segment -segment_time {chunk_duration} -c copy \"{chunk_folder}/{current_audio_name}_%03d.wav\"'\n",
+        "        run_command(split_cmd)\n",
+        "        chunk_files = sorted(glob.glob(f\"{chunk_folder}/{current_audio_name}_*.wav\"))\n",
+        "        if not chunk_files:\n",
+        "            print(f\"Warning: Gagal membuat chunk untuk {current_audio_name}. Melewatkan file ini.\")\n",
+        "            continue\n",
+        "\n",
+        "        print(f\"Memproses {len(chunk_files)} chunk dengan Demucs...\")\n",
+        "        chunk_vocals_files = []\n",
+        "        for chunk_file in chunk_files:\n",
+        "            demucs_cmd = f'python3 -m demucs.separate --two-stems vocals -n {demucs_model} \"{chunk_file}\"'\n",
+        "            run_command(demucs_cmd)\n",
+        "            base = os.path.splitext(os.path.basename(chunk_file))[0]\n",
+        "            vocals_path = f\"separated/{demucs_model}/{base}/vocals.wav\"\n",
+        "            if os.path.exists(vocals_path):\n",
+        "                chunk_vocals_files.append(os.path.abspath(vocals_path))\n",
+        "            else:\n",
+        "                print(f\"Warning: Hasil Demucs untuk {chunk_file} tidak ditemukan.\")\n",
+        "\n",
+        "        if not chunk_vocals_files:\n",
+        "            print(f\"Warning: Tidak ada vokal yang berhasil diekstrak untuk {current_audio_name}. Melewatkan file ini.\")\n",
+        "            continue\n",
+        "\n",
+        "        list_file = \"chunks_list.txt\"\n",
+        "        with open(list_file, \"w\") as f:\n",
+        "            for file in chunk_vocals_files:\n",
+        "                f.write(f\"file '{file}'\\n\")\n",
+        "        combined_vocals_path = f\"separated/{demucs_model}/{current_audio_name}_vocals.wav\"\n",
+        "        concat_cmd = f'ffmpeg -hide_banner -loglevel error -f concat -safe 0 -i \"{list_file}\" -c copy \"{combined_vocals_path}\"'\n",
+        "        run_command(concat_cmd)\n",
+        "        print(\"Penggabungan vokal dari chunk selesai.\")\n",
+        "        all_vocals_paths.append(os.path.abspath(combined_vocals_path))\n",
+        "    else:\n",
+        "        print(\"Memproses audio penuh dengan Demucs...\")\n",
+        "        demucs_cmd = f'python3 -m demucs.separate --two-stems vocals -n {demucs_model} -o \"separated\" --filename \"{current_audio_name}/{{stem}}.{{ext}}\" \"{audio_input}\"'\n",
+        "        run_command(demucs_cmd)\n",
+        "        vocals_final = f\"separated/{demucs_model}/{current_audio_name}/vocals.wav\"\n",
+        "        if os.path.exists(vocals_final):\n",
+        "            all_vocals_paths.append(os.path.abspath(vocals_final))\n",
+        "        else:\n",
+        "            print(f\"Warning: Gagal memisahkan vokal untuk {current_audio_name}.\")\n",
+        "            continue\n",
+        "    print(\"Proses pemisahan vokal selesai.\")\n",
+        "\n",
+        "# === STEP 3: Splitting Vocals (Jika mode = \"Splitting\") ===\n",
+        "if mode == \"Splitting\":\n",
+        "    print(\"\\n--- Melakukan Splitting pada Semua Hasil Vokal ---\")\n",
+        "    output_slicer_dir = f\"dataset/{project_name}\"\n",
+        "    os.makedirs(output_slicer_dir, exist_ok=True)\n",
+        "    try:\n",
+        "        import numpy as np\n",
+        "        import librosa\n",
+        "        import soundfile as sf\n",
+        "\n",
+        "        # (Fungsi Slicer dan get_rms tetap sama, disertakan di sini)\n",
+        "        def get_rms(y, frame_length=2048, hop_length=512, pad_mode=\"constant\"):\n",
+        "            padding = (int(frame_length // 2), int(frame_length // 2))\n",
+        "            y = np.pad(y, padding, mode=pad_mode)\n",
+        "            axis = -1\n",
+        "            out_strides = y.strides + (y.strides[axis],)\n",
+        "            x_shape_trimmed = list(y.shape)\n",
+        "            x_shape_trimmed[axis] -= frame_length - 1\n",
+        "            out_shape = tuple(x_shape_trimmed) + (frame_length,)\n",
+        "            xw = np.lib.stride_tricks.as_strided(y, shape=out_shape, strides=out_strides)\n",
+        "            if axis < 0:\n",
+        "                target_axis = axis - 1\n",
+        "            else:\n",
+        "                target_axis = axis + 1\n",
+        "            xw = np.moveaxis(xw, -1, target_axis)\n",
+        "            slices = [slice(None)] * xw.ndim\n",
+        "            slices[axis] = slice(0, None, hop_length)\n",
+        "            x = xw[tuple(slices)]\n",
+        "            power = np.mean(np.abs(x)**2, axis=-2, keepdims=True)\n",
+        "            return np.sqrt(power).squeeze(0)\n",
+        "\n",
+        "        class Slicer:\n",
+        "            def __init__(self, sr, threshold=-40., min_length=5000, min_interval=300, hop_size=20, max_sil_kept=5000):\n",
+        "                if not min_length >= min_interval >= hop_size:\n",
+        "                    raise ValueError('min_length >= min_interval >= hop_size harus terpenuhi')\n",
+        "                if not max_sil_kept >= hop_size:\n",
+        "                    raise ValueError('max_sil_kept >= hop_size harus terpenuhi')\n",
+        "                min_interval = sr * min_interval / 1000\n",
+        "                self.threshold = 10 ** (threshold/20.)\n",
+        "                self.hop_size = round(sr * hop_size / 1000)\n",
+        "                self.win_size = min(round(min_interval), 4 * self.hop_size)\n",
+        "                self.min_length = round(sr * min_length / 1000 / self.hop_size)\n",
+        "                self.min_interval = round(min_interval / self.hop_size)\n",
+        "                self.max_sil_kept = round(sr * max_sil_kept / 1000 / self.hop_size)\n",
+        "\n",
+        "            def _apply_slice(self, waveform, begin, end):\n",
+        "                return waveform[begin*self.hop_size: min(len(waveform), end*self.hop_size)]\n",
+        "\n",
+        "            def slice(self, waveform):\n",
+        "                if len(waveform) <= self.min_length:\n",
+        "                    return [waveform]\n",
+        "                rms_list = get_rms(waveform, frame_length=self.win_size, hop_length=self.hop_size)\n",
+        "                sil_tags = []\n",
+        "                silence_start = None\n",
+        "                clip_start = 0\n",
+        "                for i, rms in enumerate(rms_list):\n",
+        "                    if rms < self.threshold:\n",
+        "                        if silence_start is None:\n",
+        "                            silence_start = i\n",
+        "                        continue\n",
+        "                    if silence_start is None:\n",
+        "                        continue\n",
+        "                    is_leading_silence = silence_start == 0 and i > self.max_sil_kept\n",
+        "                    need_slice_middle = i - silence_start >= self.min_interval and i - clip_start >= self.min_length\n",
+        "                    if not is_leading_silence and not need_slice_middle:\n",
+        "                        silence_start = None\n",
+        "                        continue\n",
+        "                    if i - silence_start <= self.max_sil_kept:\n",
+        "                        pos = rms_list[silence_start: i+1].argmin() + silence_start\n",
+        "                        sil_tags.append((0, pos) if silence_start == 0 else (pos, pos))\n",
+        "                        clip_start = pos\n",
+        "                    elif i - silence_start <= self.max_sil_kept * 2:\n",
+        "                        pos = rms_list[i-self.max_sil_kept: silence_start+self.max_sil_kept+1].argmin() + i-self.max_sil_kept\n",
+        "                        pos_l = rms_list[silence_start: silence_start+self.max_sil_kept+1].argmin() + silence_start\n",
+        "                        pos_r = rms_list[i-self.max_sil_kept: i+1].argmin() + i-self.max_sil_kept\n",
+        "                        sil_tags.append((0, pos_r) if silence_start == 0 else (min(pos_l, pos), max(pos_r, pos)))\n",
+        "                        clip_start = pos_r\n",
+        "                    else:\n",
+        "                        pos_l = rms_list[silence_start: silence_start+self.max_sil_kept+1].argmin() + silence_start\n",
+        "                        pos_r = rms_list[i-self.max_sil_kept: i+1].argmin() + i-self.max_sil_kept\n",
+        "                        sil_tags.append((0, pos_r) if silence_start == 0 else (pos_l, pos_r))\n",
+        "                        clip_start = pos_r\n",
+        "                    silence_start = None\n",
+        "                total_frames = len(rms_list)\n",
+        "                if silence_start is not None and total_frames - silence_start >= self.min_interval:\n",
+        "                    silence_end = min(total_frames, silence_start+self.max_sil_kept)\n",
+        "                    pos = rms_list[silence_start: silence_end+1].argmin() + silence_start\n",
+        "                    sil_tags.append((pos, total_frames+1))\n",
+        "                if len(sil_tags) == 0:\n",
+        "                    return [waveform]\n",
+        "                chunks = []\n",
+        "                if sil_tags[0][0] > 0:\n",
+        "                    chunks.append(self._apply_slice(waveform, 0, sil_tags[0][0]))\n",
+        "                for i in range(len(sil_tags)-1):\n",
+        "                    chunks.append(self._apply_slice(waveform, sil_tags[i][1], sil_tags[i+1][0]))\n",
+        "                if sil_tags[-1][1] < total_frames:\n",
+        "                    chunks.append(self._apply_slice(waveform, sil_tags[-1][1], total_frames))\n",
+        "                return chunks\n",
+        "\n",
+        "        global_chunk_count = 0\n",
+        "        for vocal_file in all_vocals_paths:\n",
+        "            print(f\"Slicing {os.path.basename(vocal_file)}...\")\n",
+        "            if not os.path.exists(vocal_file):\n",
+        "                print(f\"  Warning: File vokal tidak ditemukan: {vocal_file}. Melewatkan.\")\n",
+        "                continue\n",
+        "\n",
+        "            load_sr = None if output_sr == 0 else output_sr\n",
+        "            audio, sr = librosa.load(vocal_file, sr=load_sr, mono=True)\n",
+        "\n",
+        "            slicer = Slicer(sr=sr, threshold=-40, min_length=5000, min_interval=500, hop_size=10, max_sil_kept=500)\n",
+        "            chunks = slicer.slice(audio)\n",
+        "            for chunk in chunks:\n",
+        "                sf.write(f\"{output_slicer_dir}/split_{global_chunk_count}.{output_format}\", chunk, sr)\n",
+        "                global_chunk_count += 1\n",
+        "        print(f\"\\nSplitting selesai. Total {global_chunk_count} file dibuat.\")\n",
+        "    except Exception as e:\n",
+        "        print(f\"Terjadi kesalahan saat splitting: {e}\")\n",
+        "        raise e\n",
+        "\n",
+        "# === STEP 4: Copy Hasil ke Google Drive ===\n",
+        "print(\"\\n--- Menyalin Hasil ke Google Drive ---\")\n",
+        "base_drive_folder = f\"/content/drive/MyDrive/dataset/{project_name}\"\n",
+        "vocals_drive_folder = f\"{base_drive_folder}/vocals_only\"\n",
+        "sliced_drive_folder = f\"{base_drive_folder}/sliced_mixed\"\n",
+        "\n",
+        "os.makedirs(vocals_drive_folder, exist_ok=True)\n",
+        "os.makedirs(sliced_drive_folder, exist_ok=True)\n",
+        "\n",
+        "print(f\"Menyalin vokal mentah ke: {vocals_drive_folder}\")\n",
+        "for vocal_path in all_vocals_paths:\n",
+        "    if os.path.exists(vocal_path):\n",
+        "        shutil.copy(vocal_path, vocals_drive_folder)\n",
+        "\n",
+        "if mode == \"Splitting\":\n",
+        "    print(f\"Menyalin dataset yang sudah di-slice ke: {sliced_drive_folder}\")\n",
+        "    local_sliced_folder = f\"dataset/{project_name}\"\n",
+        "    for item in os.listdir(local_sliced_folder):\n",
+        "        s = os.path.join(local_sliced_folder, item)\n",
+        "        d = os.path.join(sliced_drive_folder, item)\n",
+        "        if os.path.isdir(s):\n",
+        "            shutil.copytree(s, d, dirs_exist_ok=True)\n",
+        "        else:\n",
+        "            shutil.copy2(s, d)\n",
+        "\n",
+        "# --- Cleanup ---\n",
+        "shutil.rmtree(\"temp_audio_downloads\", ignore_errors=True)\n",
+        "shutil.rmtree(\"chunks\", ignore_errors=True)\n",
+        "shutil.rmtree(\"separated\", ignore_errors=True)\n",
+        "\n",
+        "print(\"\\nProses selesai!\")\n"
+      ],
+      "metadata": {
+        "id": "0L7br10ouMlL",
+        "cellView": "form"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}