{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "machine_shape": "hm", "gpuType": "A100", "authorship_tag": "ABX9TyPdN5espelPFPe/F1OA4L5f", "include_colab_link": true }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "accelerator": "GPU", "widgets": { "application/vnd.jupyter.widget-state+json": { "425505387f374468870cc4bcb52ea6c5": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_9b039beb3d7c4bc59ab95bd5d8a7dfcc", "IPY_MODEL_55bf104e557340e5a88962134a765f1b", "IPY_MODEL_f0768ce2c3484c4583810f461a0b742e" ], "layout": "IPY_MODEL_ff7dff340d9f41c29313ca68034be359" } }, "9b039beb3d7c4bc59ab95bd5d8a7dfcc": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_77a54e634f0d44c080eb769a4d2921b0", "placeholder": "​", "style": "IPY_MODEL_5584c9aaa4e04734bb6833cf7cf76534", "value": "Downloading (…)rt_base_ls960_14.pth: 100%" } }, "55bf104e557340e5a88962134a765f1b": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_7a2e70b96a054cdd89f73edd2474e20c", "max": 103981977, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_1120230111694b4d8e63d476b0a35454", "value": 103981977 } }, "f0768ce2c3484c4583810f461a0b742e": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_643343218af349aaa63afbcd3cbc8009", "placeholder": "​", "style": "IPY_MODEL_dfb0df17546545a4b74ed7f5f10c7a9a", "value": " 104M/104M [00:00<00:00, 406MB/s]" } }, "ff7dff340d9f41c29313ca68034be359": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "77a54e634f0d44c080eb769a4d2921b0": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5584c9aaa4e04734bb6833cf7cf76534": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "7a2e70b96a054cdd89f73edd2474e20c": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1120230111694b4d8e63d476b0a35454": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "643343218af349aaa63afbcd3cbc8009": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "dfb0df17546545a4b74ed7f5f10c7a9a": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } } } } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "view-in-github", "colab_type": "text" }, "source": [ "\"Open" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "n281rhWYnEbf", "outputId": "cf8d7edf-63ff-4b7f-9cc0-97640e113c1b" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Cloning into 'Bark-Voice-Cloning'...\n", "remote: Enumerating objects: 132, done.\u001b[K\n", "remote: Counting objects: 100% (59/59), done.\u001b[K\n", "remote: Compressing objects: 100% (59/59), done.\u001b[K\n", "remote: Total 132 (delta 30), reused 0 (delta 0), pack-reused 73\u001b[K\n", "Receiving objects: 100% (132/132), 225.44 KiB | 15.03 MiB/s, done.\n", "Resolving deltas: 100% (38/38), done.\n" ] } ], "source": [ "!git clone https://github.com/KevinWang676/Bark-Voice-Cloning.git" ] }, { "cell_type": "code", "source": [ "cd Bark-Voice-Cloning/" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "uyyMhQgBnJLG", "outputId": "4a91aa03-787c-41e8-b59d-dbddc9eed3b8" }, "execution_count": 10, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "/content/Bark-Voice-Cloning\n" ] } ] }, { "cell_type": "code", "source": [ "pip install -r requirements.txt" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "fm8b-BXPnPDb", "outputId": "df4bfdec-d418-4edd-d41b-7cf4d40a6a2e" }, "execution_count": 6, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Ignoring fairseq: markers 'platform_system == \"Windows\"' don't match your environment\n", "Ignoring soundfile: markers 'platform_system == \"Windows\"' don't match your environment\n", "Requirement already satisfied: fairseq in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 1)) (0.12.2)\n", "Requirement already satisfied: audiolm-pytorch in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 3)) (1.1.4)\n", "Requirement already satisfied: gradio in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 4)) (3.34.0)\n", "Requirement already satisfied: funcy in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 5)) (2.0)\n", "Requirement already satisfied: linkify in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 6)) (1.4)\n", "Requirement already satisfied: mutagen in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 7)) (1.46.0)\n", "Requirement already satisfied: pytorch_seed in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 8)) (0.2.0)\n", "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 9)) (6.0)\n", "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 10)) (0.1.99)\n", "Requirement already satisfied: sox in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 12)) (1.4.1)\n", "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 13)) (4.30.1)\n", "Requirement already satisfied: cffi in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (1.15.1)\n", "Requirement already satisfied: cython in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (0.29.34)\n", "Requirement already satisfied: hydra-core<1.1,>=1.0.7 in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (1.0.7)\n", "Requirement already satisfied: omegaconf<2.1 in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (2.0.6)\n", "Requirement already satisfied: regex in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (2022.10.31)\n", "Requirement already satisfied: sacrebleu>=1.4.12 in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (2.3.1)\n", "Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (2.0.1+cu118)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (4.65.0)\n", "Requirement already satisfied: bitarray in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (2.7.5)\n", "Requirement already satisfied: torchaudio>=0.8.0 in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (2.0.2+cu118)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from fairseq->-r requirements.txt (line 1)) (1.22.4)\n", "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (0.20.3)\n", "Requirement already satisfied: beartype in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (0.14.1)\n", "Requirement already satisfied: einops>=0.6.1 in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (0.6.1)\n", "Requirement already satisfied: ema-pytorch>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (0.2.3)\n", "Requirement already satisfied: encodec in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (0.1.1)\n", "Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (1.2.0)\n", "Requirement already satisfied: lion-pytorch in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (0.1.2)\n", "Requirement already satisfied: local-attention>=1.8.4 in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (1.8.6)\n", "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (1.2.2)\n", "Requirement already satisfied: vector-quantize-pytorch>=1.5.14 in /usr/local/lib/python3.10/dist-packages (from audiolm-pytorch->-r requirements.txt (line 3)) (1.6.11)\n", "Requirement already satisfied: aiofiles in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (23.1.0)\n", "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (3.8.4)\n", "Requirement already satisfied: altair>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (4.2.2)\n", "Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (0.97.0)\n", "Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (0.3.0)\n", "Requirement already satisfied: gradio-client>=0.2.6 in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (0.2.6)\n", "Requirement already satisfied: httpx in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (0.24.1)\n", "Requirement already satisfied: huggingface-hub>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (0.15.1)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (3.1.2)\n", "Requirement already satisfied: markdown-it-py[linkify]>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (2.2.0)\n", "Requirement already satisfied: markupsafe in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (2.1.2)\n", "Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (3.7.1)\n", "Requirement already satisfied: mdit-py-plugins<=0.3.3 in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (0.3.3)\n", "Requirement already satisfied: orjson in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (3.9.1)\n", "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (1.5.3)\n", "Requirement already satisfied: pillow in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (8.4.0)\n", "Requirement already satisfied: pydantic in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (1.10.7)\n", "Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (0.25.1)\n", "Requirement already satisfied: pygments>=2.12.0 in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (2.14.0)\n", "Requirement already satisfied: python-multipart in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (0.0.6)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (2.27.1)\n", "Requirement already satisfied: semantic-version in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (2.10.0)\n", "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (4.5.0)\n", "Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (0.22.0)\n", "Requirement already satisfied: websockets>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio->-r requirements.txt (line 4)) (11.0.3)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers->-r requirements.txt (line 13)) (3.12.0)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers->-r requirements.txt (line 13)) (23.1)\n", "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers->-r requirements.txt (line 13)) (0.13.3)\n", "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers->-r requirements.txt (line 13)) (0.3.1)\n", "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio->-r requirements.txt (line 4)) (0.4)\n", "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio->-r requirements.txt (line 4)) (4.3.3)\n", "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio->-r requirements.txt (line 4)) (0.12.0)\n", "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client>=0.2.6->gradio->-r requirements.txt (line 4)) (2023.4.0)\n", "Requirement already satisfied: antlr4-python3-runtime==4.8 in /usr/local/lib/python3.10/dist-packages (from hydra-core<1.1,>=1.0.7->fairseq->-r requirements.txt (line 1)) (4.8)\n", "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio->-r requirements.txt (line 4)) (0.1.2)\n", "Requirement already satisfied: linkify-it-py<3,>=1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio->-r requirements.txt (line 4)) (2.0.2)\n", "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->gradio->-r requirements.txt (line 4)) (2.8.2)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->gradio->-r requirements.txt (line 4)) (2022.7.1)\n", "Requirement already satisfied: portalocker in /usr/local/lib/python3.10/dist-packages (from sacrebleu>=1.4.12->fairseq->-r requirements.txt (line 1)) (2.7.0)\n", "Requirement already satisfied: tabulate>=0.8.9 in /usr/local/lib/python3.10/dist-packages (from sacrebleu>=1.4.12->fairseq->-r requirements.txt (line 1)) (0.8.10)\n", "Requirement already satisfied: colorama in /usr/local/lib/python3.10/dist-packages (from sacrebleu>=1.4.12->fairseq->-r requirements.txt (line 1)) (0.4.6)\n", "Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from sacrebleu>=1.4.12->fairseq->-r requirements.txt (line 1)) (4.9.2)\n", "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->fairseq->-r requirements.txt (line 1)) (1.11.1)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->fairseq->-r requirements.txt (line 1)) (3.1)\n", "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch->fairseq->-r requirements.txt (line 1)) (2.0.0)\n", "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch->fairseq->-r requirements.txt (line 1)) (3.25.2)\n", "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch->fairseq->-r requirements.txt (line 1)) (16.0.5)\n", "Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio->-r requirements.txt (line 4)) (8.1.3)\n", "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio->-r requirements.txt (line 4)) (0.14.0)\n", "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate->audiolm-pytorch->-r requirements.txt (line 3)) (5.9.5)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio->-r requirements.txt (line 4)) (23.1.0)\n", "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio->-r requirements.txt (line 4)) (2.0.12)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio->-r requirements.txt (line 4)) (6.0.4)\n", "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio->-r requirements.txt (line 4)) (4.0.2)\n", "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio->-r requirements.txt (line 4)) (1.9.2)\n", "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio->-r requirements.txt (line 4)) (1.3.3)\n", "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio->-r requirements.txt (line 4)) (1.3.1)\n", "Requirement already satisfied: pycparser in /usr/local/lib/python3.10/dist-packages (from cffi->fairseq->-r requirements.txt (line 1)) (2.21)\n", "Requirement already satisfied: starlette<0.28.0,>=0.27.0 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio->-r requirements.txt (line 4)) (0.27.0)\n", "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx->gradio->-r requirements.txt (line 4)) (2022.12.7)\n", "Requirement already satisfied: httpcore<0.18.0,>=0.15.0 in /usr/local/lib/python3.10/dist-packages (from httpx->gradio->-r requirements.txt (line 4)) (0.17.2)\n", "Requirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx->gradio->-r requirements.txt (line 4)) (3.4)\n", "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio->-r requirements.txt (line 4)) (1.3.0)\n", "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio->-r requirements.txt (line 4)) (1.0.7)\n", "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio->-r requirements.txt (line 4)) (0.11.0)\n", "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio->-r requirements.txt (line 4)) (4.39.3)\n", "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio->-r requirements.txt (line 4)) (1.4.4)\n", "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio->-r requirements.txt (line 4)) (3.0.9)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->gradio->-r requirements.txt (line 4)) (1.26.15)\n", "Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->audiolm-pytorch->-r requirements.txt (line 3)) (1.10.1)\n", "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->audiolm-pytorch->-r requirements.txt (line 3)) (3.1.0)\n", "Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from httpcore<0.18.0,>=0.15.0->httpx->gradio->-r requirements.txt (line 4)) (3.6.2)\n", "Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio->-r requirements.txt (line 4)) (0.19.3)\n", "Requirement already satisfied: uc-micro-py in /usr/local/lib/python3.10/dist-packages (from linkify-it-py<3,>=1->markdown-it-py[linkify]>=2.0.0->gradio->-r requirements.txt (line 4)) (1.0.2)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->gradio->-r requirements.txt (line 4)) (1.16.0)\n", "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->fairseq->-r requirements.txt (line 1)) (1.3.0)\n" ] } ] }, { "cell_type": "code", "source": [ "from cProfile import label\n", "import dataclasses\n", "from distutils.command.check import check\n", "from doctest import Example\n", "import gradio as gr\n", "import os\n", "import sys\n", "import numpy as np\n", "import logging\n", "import torch\n", "import pytorch_seed\n", "import time\n", "\n", "from xml.sax import saxutils\n", "from bark.api import generate_with_settings\n", "from bark.api import save_as_prompt\n", "from util.settings import Settings\n", "#import nltk\n", "\n", "from bark import SAMPLE_RATE\n", "from cloning.clonevoice import clone_voice\n", "from bark.generation import SAMPLE_RATE, preload_models, _load_history_prompt, codec_decode\n", "from scipy.io.wavfile import write as write_wav\n", "from util.parseinput import split_and_recombine_text, build_ssml, is_ssml, create_clips_from_ssml\n", "from datetime import datetime\n", "from tqdm.auto import tqdm\n", "from util.helper import create_filename, add_id3_tag\n", "from swap_voice import swap_voice_from_audio\n", "from training.training_prepare import prepare_semantics_from_text, prepare_wavs_from_semantics\n", "from training.train import training_prepare_files, train\n", "\n", "settings = Settings('config.yaml')\n", "\n", "\n", "def generate_text_to_speech(text, selected_speaker, text_temp, waveform_temp, eos_prob, quick_generation, complete_settings, seed, batchcount, progress=gr.Progress(track_tqdm=True)):\n", " # Chunk the text into smaller pieces then combine the generated audio\n", "\n", " # generation settings\n", " if selected_speaker == 'None':\n", " selected_speaker = None\n", "\n", " voice_name = selected_speaker\n", "\n", " if text == None or len(text) < 1:\n", " if selected_speaker == None:\n", " raise gr.Error('No text entered!')\n", "\n", " # Extract audio data from speaker if no text and speaker selected\n", " voicedata = _load_history_prompt(voice_name)\n", " audio_arr = codec_decode(voicedata[\"fine_prompt\"])\n", " result = create_filename(settings.output_folder_path, \"None\", \"extract\",\".wav\")\n", " save_wav(audio_arr, result)\n", " return result\n", "\n", " if batchcount < 1:\n", " batchcount = 1\n", "\n", "\n", " silenceshort = np.zeros(int((float(settings.silence_sentence) / 1000.0) * SAMPLE_RATE), dtype=np.int16) # quarter second of silence\n", " silencelong = np.zeros(int((float(settings.silence_speakers) / 1000.0) * SAMPLE_RATE), dtype=np.float32) # half a second of silence\n", " use_last_generation_as_history = \"Use last generation as history\" in complete_settings\n", " save_last_generation = \"Save generation as Voice\" in complete_settings\n", " for l in range(batchcount):\n", " currentseed = seed\n", " if seed != None and seed > 2**32 - 1:\n", " logger.warning(f\"Seed {seed} > 2**32 - 1 (max), setting to random\")\n", " currentseed = None\n", " if currentseed == None or currentseed <= 0:\n", " currentseed = np.random.default_rng().integers(1, 2**32 - 1)\n", " assert(0 < currentseed and currentseed < 2**32)\n", "\n", " progress(0, desc=\"Generating\")\n", "\n", " full_generation = None\n", "\n", " all_parts = []\n", " complete_text = \"\"\n", " text = text.lstrip()\n", " if is_ssml(text):\n", " list_speak = create_clips_from_ssml(text)\n", " prev_speaker = None\n", " for i, clip in tqdm(enumerate(list_speak), total=len(list_speak)):\n", " selected_speaker = clip[0]\n", " # Add pause break between speakers\n", " if i > 0 and selected_speaker != prev_speaker:\n", " all_parts += [silencelong.copy()]\n", " prev_speaker = selected_speaker\n", " text = clip[1]\n", " text = saxutils.unescape(text)\n", " if selected_speaker == \"None\":\n", " selected_speaker = None\n", "\n", " print(f\"\\nGenerating Text ({i+1}/{len(list_speak)}) -> {selected_speaker} (Seed {currentseed}):`{text}`\")\n", " complete_text += text\n", " with pytorch_seed.SavedRNG(currentseed):\n", " audio_array = generate_with_settings(text_prompt=text, voice_name=selected_speaker, semantic_temp=text_temp, coarse_temp=waveform_temp, eos_p=eos_prob)\n", " currentseed = torch.random.initial_seed()\n", " if len(list_speak) > 1:\n", " filename = create_filename(settings.output_folder_path, currentseed, \"audioclip\",\".wav\")\n", " save_wav(audio_array, filename)\n", " add_id3_tag(filename, text, selected_speaker, currentseed)\n", "\n", " all_parts += [audio_array]\n", " else:\n", " texts = split_and_recombine_text(text, settings.input_text_desired_length, settings.input_text_max_length)\n", " for i, text in tqdm(enumerate(texts), total=len(texts)):\n", " print(f\"\\nGenerating Text ({i+1}/{len(texts)}) -> {selected_speaker} (Seed {currentseed}):`{text}`\")\n", " complete_text += text\n", " if quick_generation == True:\n", " with pytorch_seed.SavedRNG(currentseed):\n", " audio_array = generate_with_settings(text_prompt=text, voice_name=selected_speaker, semantic_temp=text_temp, coarse_temp=waveform_temp, eos_p=eos_prob)\n", " currentseed = torch.random.initial_seed()\n", " else:\n", " full_output = use_last_generation_as_history or save_last_generation\n", " if full_output:\n", " full_generation, audio_array = generate_with_settings(text_prompt=text, voice_name=voice_name, semantic_temp=text_temp, coarse_temp=waveform_temp, eos_p=eos_prob, output_full=True)\n", " else:\n", " audio_array = generate_with_settings(text_prompt=text, voice_name=voice_name, semantic_temp=text_temp, coarse_temp=waveform_temp, eos_p=eos_prob)\n", "\n", " # Noticed this in the HF Demo - convert to 16bit int -32767/32767 - most used audio format \n", " # audio_array = (audio_array * 32767).astype(np.int16)\n", "\n", " if len(texts) > 1:\n", " filename = create_filename(settings.output_folder_path, currentseed, \"audioclip\",\".wav\")\n", " save_wav(audio_array, filename)\n", " add_id3_tag(filename, text, selected_speaker, currentseed)\n", "\n", " if quick_generation == False and (save_last_generation == True or use_last_generation_as_history == True):\n", " # save to npz\n", " voice_name = create_filename(settings.output_folder_path, seed, \"audioclip\", \".npz\")\n", " save_as_prompt(voice_name, full_generation)\n", " if use_last_generation_as_history:\n", " selected_speaker = voice_name\n", "\n", " all_parts += [audio_array]\n", " # Add short pause between sentences\n", " if text[-1] in \"!?.\\n\" and i > 1:\n", " all_parts += [silenceshort.copy()]\n", "\n", " # save & play audio\n", " result = create_filename(settings.output_folder_path, currentseed, \"final\",\".wav\")\n", " save_wav(np.concatenate(all_parts), result)\n", " # write id3 tag with text truncated to 60 chars, as a precaution...\n", " add_id3_tag(result, complete_text, selected_speaker, currentseed)\n", "\n", " return result\n", "\n", "\n", "\n", "def save_wav(audio_array, filename):\n", " write_wav(filename, SAMPLE_RATE, audio_array)\n", "\n", "def save_voice(filename, semantic_prompt, coarse_prompt, fine_prompt):\n", " np.savez_compressed(\n", " filename,\n", " semantic_prompt=semantic_prompt,\n", " coarse_prompt=coarse_prompt,\n", " fine_prompt=fine_prompt\n", " )\n", " \n", "\n", "def on_quick_gen_changed(checkbox):\n", " if checkbox == False:\n", " return gr.CheckboxGroup.update(visible=True)\n", " return gr.CheckboxGroup.update(visible=False)\n", "\n", "def delete_output_files(checkbox_state):\n", " if checkbox_state:\n", " outputs_folder = os.path.join(os.getcwd(), settings.output_folder_path)\n", " if os.path.exists(outputs_folder):\n", " purgedir(outputs_folder)\n", " return False\n", "\n", "\n", "# https://stackoverflow.com/a/54494779\n", "def purgedir(parent):\n", " for root, dirs, files in os.walk(parent): \n", " for item in files:\n", " # Delete subordinate files \n", " filespec = os.path.join(root, item)\n", " os.unlink(filespec)\n", " for item in dirs:\n", " # Recursively perform this operation for subordinate directories \n", " purgedir(os.path.join(root, item))\n", "\n", "def convert_text_to_ssml(text, selected_speaker):\n", " return build_ssml(text, selected_speaker)\n", "\n", "\n", "def training_prepare(selected_step, num_text_generations, progress=gr.Progress(track_tqdm=True)):\n", " if selected_step == prepare_training_list[0]:\n", " prepare_semantics_from_text()\n", " else:\n", " prepare_wavs_from_semantics()\n", " return None\n", "\n", "\n", "def start_training(save_model_epoch, max_epochs, progress=gr.Progress(track_tqdm=True)):\n", " training_prepare_files(\"./training/data/\", \"./training/data/checkpoint/hubert_base_ls960.pt\")\n", " train(\"./training/data/\", save_model_epoch, max_epochs)\n", " return None\n", "\n", "\n", "\n", "def apply_settings(themes, input_server_name, input_server_port, input_server_public, input_desired_len, input_max_len, input_silence_break, input_silence_speaker):\n", " settings.selected_theme = themes\n", " settings.server_name = input_server_name\n", " settings.server_port = input_server_port\n", " settings.server_share = input_server_public\n", " settings.input_text_desired_length = input_desired_len\n", " settings.input_text_max_length = input_max_len\n", " settings.silence_sentence = input_silence_break\n", " settings.silence_speaker = input_silence_speaker\n", " settings.save()\n", "\n", "def restart():\n", " global restart_server\n", " restart_server = True\n", "\n", "\n", "def create_version_html():\n", " python_version = \".\".join([str(x) for x in sys.version_info[0:3]])\n", " versions_html = f\"\"\"\n", "python: {python_version}\n", " • \n", "torch: {getattr(torch, '__long_version__',torch.__version__)}\n", " • \n", "gradio: {gr.__version__}\n", "\"\"\"\n", " return versions_html\n", "\n", " \n", "\n", "logger = logging.getLogger(__name__)\n", "APPTITLE = \"Bark Voice Cloning UI\"\n", "\n", "\n", "autolaunch = False\n", "\n", "if len(sys.argv) > 1:\n", " autolaunch = \"-autolaunch\" in sys.argv\n", "\n", "\n", "if torch.cuda.is_available() == False:\n", " os.environ['BARK_FORCE_CPU'] = 'True'\n", " logger.warning(\"No CUDA detected, fallback to CPU!\")\n", "\n", "print(f'smallmodels={os.environ.get(\"SUNO_USE_SMALL_MODELS\", False)}')\n", "print(f'enablemps={os.environ.get(\"SUNO_ENABLE_MPS\", False)}')\n", "print(f'offloadcpu={os.environ.get(\"SUNO_OFFLOAD_CPU\", False)}')\n", "print(f'forcecpu={os.environ.get(\"BARK_FORCE_CPU\", False)}')\n", "print(f'autolaunch={autolaunch}\\n\\n')\n", "\n", "#print(\"Updating nltk\\n\")\n", "#nltk.download('punkt')\n", "\n", "print(\"Preloading Models\\n\")\n", "preload_models()\n", "\n", "available_themes = [\"Default\", \"gradio/glass\", \"gradio/monochrome\", \"gradio/seafoam\", \"gradio/soft\", \"gstaff/xkcd\", \"freddyaboulton/dracula_revamped\", \"ysharma/steampunk\"]\n", "tokenizer_language_list = [\"de\",\"en\", \"pl\"]\n", "prepare_training_list = [\"Step 1: Semantics from Text\",\"Step 2: WAV from Semantics\"]\n", "\n", "seed = -1\n", "server_name = settings.server_name\n", "if len(server_name) < 1:\n", " server_name = None\n", "server_port = settings.server_port\n", "if server_port <= 0:\n", " server_port = None\n", "global run_server\n", "global restart_server\n", "\n", "run_server = True\n", "\n", "while run_server:\n", " # Collect all existing speakers/voices in dir\n", " speakers_list = []\n", "\n", " for root, dirs, files in os.walk(\"./bark/assets/prompts\"):\n", " for file in files:\n", " if file.endswith(\".npz\"):\n", " pathpart = root.replace(\"./bark/assets/prompts\", \"\")\n", " name = os.path.join(pathpart, file[:-4])\n", " if name.startswith(\"/\") or name.startswith(\"\\\\\"):\n", " name = name[1:]\n", " speakers_list.append(name)\n", "\n", " speakers_list = sorted(speakers_list, key=lambda x: x.lower())\n", " speakers_list.insert(0, 'None')\n", "\n", " print(f'Launching {APPTITLE} Server')\n", "\n", " # Create Gradio Blocks\n", "\n", " with gr.Blocks(title=f\"{APPTITLE}\", mode=f\"{APPTITLE}\", theme=settings.selected_theme) as barkgui:\n", " with gr.Row():\n", " with gr.Column():\n", " gr.Markdown(f\"### [{APPTITLE}](https://github.com/KevinWang676/Bark-Voice-Cloning)\")\n", " with gr.Column():\n", " gr.HTML(create_version_html(), elem_id=\"versions\")\n", "\n", " with gr.Tab(\"Clone Voice\"):\n", " with gr.Row():\n", " input_audio_filename = gr.Audio(label=\"Input audio.wav\", source=\"upload\", type=\"filepath\")\n", " #transcription_text = gr.Textbox(label=\"Transcription Text\", lines=1, placeholder=\"Enter Text of your Audio Sample here...\")\n", " with gr.Row():\n", " with gr.Column():\n", " initialname = \"/content/Bark-Voice-Cloning/bark/assets/prompts/file\"\n", " output_voice = gr.Textbox(label=\"Filename of trained Voice (do not change the initial name)\", lines=1, placeholder=initialname, value=initialname)\n", " with gr.Column():\n", " tokenizerlang = gr.Dropdown(tokenizer_language_list, label=\"Base Language Tokenizer\", value=tokenizer_language_list[1])\n", " with gr.Row():\n", " clone_voice_button = gr.Button(\"Create Voice\")\n", " with gr.Row():\n", " dummy = gr.Text(label=\"Progress\")\n", " npz_file = gr.File(label=\".npz file\")\n", " speakers_list.insert(0, npz_file) # add prompt\n", "\n", " with gr.Tab(\"TTS\"):\n", " with gr.Row():\n", " with gr.Column():\n", " placeholder = \"Enter text here.\"\n", " input_text = gr.Textbox(label=\"Input Text\", lines=4, placeholder=placeholder)\n", " with gr.Column():\n", " seedcomponent = gr.Number(label=\"Seed (default -1 = Random)\", precision=0, value=-1)\n", " batchcount = gr.Number(label=\"Batch count\", precision=0, value=1)\n", " with gr.Row():\n", " with gr.Column():\n", " examples = [\n", " \"Special meanings: [laughter] [laughs] [sighs] [music] [gasps] [clears throat] MAN: WOMAN:\",\n", " \"♪ Never gonna make you cry, never gonna say goodbye, never gonna tell a lie and hurt you ♪\",\n", " \"And now — a picture of a larch [laughter]\",\n", " \"\"\"\n", " WOMAN: I would like an oatmilk latte please.\n", " MAN: Wow, that's expensive!\n", " \"\"\",\n", " \"\"\"\n", " \n", " Look at that drunk guy!\n", " Who is he?\n", " WOMAN: [clears throat] 10 years ago, he proposed me and I rejected him.\n", " Oh my God [laughs] he is still celebrating\n", " \"\"\"\n", " ]\n", " examples = gr.Examples(examples=examples, inputs=input_text)\n", " with gr.Column():\n", " convert_to_ssml_button = gr.Button(\"Convert Input Text to SSML\")\n", "\n", " with gr.Row():\n", " with gr.Column():\n", " gr.Markdown(\"[Voice Prompt Library](https://suno-ai.notion.site/8b8e8749ed514b0cbf3f699013548683?v=bc67cff786b04b50b3ceb756fd05f68c)\")\n", " speaker = gr.Dropdown(speakers_list, value=speakers_list[0], label=\"Voice\")\n", " \n", " with gr.Column():\n", " text_temp = gr.Slider(0.1, 1.0, value=0.6, label=\"Generation Temperature\", info=\"1.0 more diverse, 0.1 more conservative\")\n", " waveform_temp = gr.Slider(0.1, 1.0, value=0.7, label=\"Waveform temperature\", info=\"1.0 more diverse, 0.1 more conservative\")\n", "\n", " with gr.Row():\n", " with gr.Column():\n", " quick_gen_checkbox = gr.Checkbox(label=\"Quick Generation\", value=True)\n", " settings_checkboxes = [\"Use last generation as history\", \"Save generation as Voice\"]\n", " complete_settings = gr.CheckboxGroup(choices=settings_checkboxes, value=settings_checkboxes, label=\"Detailed Generation Settings\", type=\"value\", interactive=True, visible=False)\n", " with gr.Column():\n", " eos_prob = gr.Slider(0.0, 0.5, value=0.05, label=\"End of sentence probability\")\n", "\n", " with gr.Row():\n", " with gr.Column():\n", " tts_create_button = gr.Button(\"Generate\")\n", " with gr.Column():\n", " hidden_checkbox = gr.Checkbox(visible=False)\n", " button_stop_generation = gr.Button(\"Stop generation\")\n", " with gr.Row():\n", " output_audio = gr.Audio(label=\"Generated Audio\", type=\"filepath\")\n", "\n", " with gr.Tab(\"Swap Voice\"):\n", " with gr.Row():\n", " swap_audio_filename = gr.Audio(label=\"Input audio.wav to swap voice\", source=\"upload\", type=\"filepath\")\n", " with gr.Row():\n", " with gr.Column():\n", " swap_tokenizer_lang = gr.Dropdown(tokenizer_language_list, label=\"Base Language Tokenizer\", value=tokenizer_language_list[1])\n", " swap_seed = gr.Number(label=\"Seed (default -1 = Random)\", precision=0, value=-1)\n", " with gr.Column():\n", " speaker_swap = gr.Dropdown(speakers_list, value=speakers_list[0], label=\"Voice\")\n", " swap_batchcount = gr.Number(label=\"Batch count\", precision=0, value=1)\n", " with gr.Row():\n", " swap_voice_button = gr.Button(\"Swap Voice\")\n", " with gr.Row():\n", " output_swap = gr.Audio(label=\"Generated Audio\", type=\"filepath\")\n", "\n", " \n", " quick_gen_checkbox.change(fn=on_quick_gen_changed, inputs=quick_gen_checkbox, outputs=complete_settings)\n", " convert_to_ssml_button.click(convert_text_to_ssml, inputs=[input_text, speaker],outputs=input_text)\n", " gen_click = tts_create_button.click(generate_text_to_speech, inputs=[input_text, speaker, text_temp, waveform_temp, eos_prob, quick_gen_checkbox, complete_settings, seedcomponent, batchcount],outputs=output_audio)\n", " button_stop_generation.click(fn=None, inputs=None, outputs=None, cancels=[gen_click])\n", " \n", "\n", "\n", " swap_voice_button.click(swap_voice_from_audio, inputs=[swap_audio_filename, speaker_swap, swap_tokenizer_lang, swap_seed, swap_batchcount], outputs=output_swap)\n", " clone_voice_button.click(clone_voice, inputs=[input_audio_filename, output_voice], outputs=[dummy, npz_file])\n", "\n", "\n", " restart_server = False\n", " try:\n", " barkgui.queue().launch(show_error=True)\n", " except:\n", " restart_server = True\n", " run_server = False\n", " try:\n", " while restart_server == False:\n", " time.sleep(1.0)\n", " except (KeyboardInterrupt, OSError):\n", " print(\"Keyboard interruption in main thread... closing server.\")\n", " run_server = False\n", " barkgui.close()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 981, "referenced_widgets": [ "425505387f374468870cc4bcb52ea6c5", "9b039beb3d7c4bc59ab95bd5d8a7dfcc", "55bf104e557340e5a88962134a765f1b", "f0768ce2c3484c4583810f461a0b742e", "ff7dff340d9f41c29313ca68034be359", "77a54e634f0d44c080eb769a4d2921b0", "5584c9aaa4e04734bb6833cf7cf76534", "7a2e70b96a054cdd89f73edd2474e20c", "1120230111694b4d8e63d476b0a35454", "643343218af349aaa63afbcd3cbc8009", "dfb0df17546545a4b74ed7f5f10c7a9a" ] }, "id": "jDsXfOlEnTO-", "outputId": "debf279f-7788-411f-ee2b-4a0522e20122" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "smallmodels=False\n", "enablemps=False\n", "offloadcpu=False\n", "forcecpu=False\n", "autolaunch=False\n", "\n", "\n", "Preloading Models\n", "\n", "Launching Bark Voice Cloning UI Server\n", "Setting queue=True in a Colab notebook requires sharing enabled. Setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n", "\n", "Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n", "Running on public URL: https://5fbed86c1148a1f8e5.gradio.live\n", "\n", "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "" ], "text/html": [ "
" ] }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "Downloading HuBERT base model from https://dl.fbaipublicfiles.com/hubert/hubert_base_ls960.pt\n", "Downloaded HuBERT\n", "en_tokenizer.pth not found. Downloading HuBERT custom tokenizer\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "Downloading (…)rt_base_ls960_14.pth: 0%| | 0.00/104M [00:00 file (Seed 529525761):`Authors are required to disclose financial or non-financial interests that are directly or indirectly related to`\n" ] } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "Mt5lkF1gnX54" }, "execution_count": null, "outputs": [] } ] }