tortoise_tts.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_pIZ3ZXNp7cf"
      },
      "source": [
        "Welcome to Tortoise! 🐢🐢🐢🐢\n",
        "\n",
        "Before you begin, I **strongly** recommend you turn on a GPU runtime.\n",
        "\n",
        "There's a reason this is called \"Tortoise\" - this model takes up to a minute to perform inference for a single sentence on a GPU. Expect waits on the order of hours on a CPU."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JrK20I32grP6",
        "outputId": "84d96fac-27d9-43f0-c1f7-71423d435de7"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'tortoise-tts-fast'...\n",
            "remote: Enumerating objects: 2314, done.\u001b[K\n",
            "remote: Total 2314 (delta 0), reused 0 (delta 0), pack-reused 2314 (from 1)\u001b[K\n",
            "Receiving objects: 100% (2314/2314), 105.07 MiB | 13.98 MiB/s, done.\n",
            "Resolving deltas: 100% (1070/1070), done.\n",
            "Updating files: 100% (697/697), done.\n",
            "/content/tortoise-tts-fast\n",
            "Ignoring backports-zoneinfo: markers 'python_version >= \"3.8\" and python_version < \"3.9\"' don't match your environment\n",
            "Collecting bigvgan@ git+https://github.com/152334H/BigVGAN.git@HEAD (from -r requirements.txt (line 38))\n",
            "\u001b[31mERROR: Can't verify hashes for these requirements because we don't have a way to hash version control repositories:\n",
            "    bigvgan@ git+https://github.com/152334H/BigVGAN.git@HEAD from git+https://github.com/152334H/BigVGAN.git@HEAD (from -r requirements.txt (line 38))\u001b[0m\u001b[31m\n",
            "\u001b[0mObtaining file:///content/tortoise-tts-fast\n",
            "  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Checking if build backend supports build_editable ... \u001b[?25l\u001b[?25hdone\n",
            "  Getting requirements to build editable ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing editable metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting bigvgan@ git+https://github.com/152334H/BigVGAN.git (from TorToiSe==3.0.0)\n",
            "  Cloning https://github.com/152334H/BigVGAN.git to /tmp/pip-install-qgzafhnt/bigvgan_a9f4b028f70f4428b70dabc14bc734c4\n",
            "  Running command git clone --filter=blob:none --quiet https://github.com/152334H/BigVGAN.git /tmp/pip-install-qgzafhnt/bigvgan_a9f4b028f70f4428b70dabc14bc734c4\n",
            "  Resolved https://github.com/152334H/BigVGAN.git to commit b10aaeea6ff7e5704d4f8198071cf9a4c174e78a\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting Unidecode<2.0.0,>=1.3.6 (from TorToiSe==3.0.0)\n",
            "  Downloading Unidecode-1.3.8-py3-none-any.whl.metadata (13 kB)\n",
            "Collecting einops<0.7.0,>=0.6.0 (from TorToiSe==3.0.0)\n",
            "  Downloading einops-0.6.1-py3-none-any.whl.metadata (12 kB)\n",
            "Collecting gdown<5.0.0,>=4.6.4 (from TorToiSe==3.0.0)\n",
            "  Downloading gdown-4.7.3-py3-none-any.whl.metadata (4.4 kB)\n",
            "Collecting inflect<7.0.0,>=6.0.2 (from TorToiSe==3.0.0)\n",
            "  Downloading inflect-6.2.0-py3-none-any.whl.metadata (21 kB)\n",
            "Collecting k-diffusion<0.0.15,>=0.0.14 (from TorToiSe==3.0.0)\n",
            "  Downloading k_diffusion-0.0.14-py3-none-any.whl.metadata (3.8 kB)\n",
            "Collecting librosa<0.9.0,>=0.8.1 (from TorToiSe==3.0.0)\n",
            "  Downloading librosa-0.8.1-py3-none-any.whl.metadata (6.8 kB)\n",
            "Collecting numba<0.57.0,>=0.56.4 (from TorToiSe==3.0.0)\n",
            "  Downloading numba-0.56.4.tar.gz (2.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m31.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n",
            "  \n",
            "  \u001b[31m×\u001b[0m \u001b[32mpython setup.py egg_info\u001b[0m did not run successfully.\n",
            "  \u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n",
            "  \u001b[31m╰─>\u001b[0m See above for output.\n",
            "  \n",
            "  \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25herror\n",
            "\u001b[1;31merror\u001b[0m: \u001b[1mmetadata-generation-failed\u001b[0m\n",
            "\n",
            "\u001b[31m×\u001b[0m Encountered error while generating package metadata.\n",
            "\u001b[31m╰─>\u001b[0m See above for output.\n",
            "\n",
            "\u001b[1;35mnote\u001b[0m: This is an issue with the package mentioned above, not pip.\n",
            "\u001b[1;36mhint\u001b[0m: See above for details.\n",
            "Collecting git+https://github.com/152334H/BigVGAN.git\n",
            "  Cloning https://github.com/152334H/BigVGAN.git to /tmp/pip-req-build-b4zuo3g4\n",
            "  Running command git clone --filter=blob:none --quiet https://github.com/152334H/BigVGAN.git /tmp/pip-req-build-b4zuo3g4\n",
            "  Resolved https://github.com/152334H/BigVGAN.git to commit b10aaeea6ff7e5704d4f8198071cf9a4c174e78a\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: torch in /usr/local/lib/python3.11/dist-packages (from BigVGAN==0.0.1) (2.5.1+cu124)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from BigVGAN==0.0.1) (1.26.4)\n",
            "Collecting librosa==0.8.1 (from BigVGAN==0.0.1)\n",
            "  Using cached librosa-0.8.1-py3-none-any.whl.metadata (6.8 kB)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.11/dist-packages (from BigVGAN==0.0.1) (1.13.1)\n",
            "Requirement already satisfied: soundfile in /usr/local/lib/python3.11/dist-packages (from BigVGAN==0.0.1) (0.13.1)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.11/dist-packages (from BigVGAN==0.0.1) (3.10.0)\n",
            "Collecting pesq (from BigVGAN==0.0.1)\n",
            "  Downloading pesq-0.0.4.tar.gz (38 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting auraloss (from BigVGAN==0.0.1)\n",
            "  Downloading auraloss-0.4.0-py3-none-any.whl.metadata (8.0 kB)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from BigVGAN==0.0.1) (4.67.1)\n",
            "Requirement already satisfied: audioread>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from librosa==0.8.1->BigVGAN==0.0.1) (3.0.1)\n",
            "Requirement already satisfied: scikit-learn!=0.19.0,>=0.14.0 in /usr/local/lib/python3.11/dist-packages (from librosa==0.8.1->BigVGAN==0.0.1) (1.6.1)\n",
            "Requirement already satisfied: joblib>=0.14 in /usr/local/lib/python3.11/dist-packages (from librosa==0.8.1->BigVGAN==0.0.1) (1.4.2)\n",
            "Requirement already satisfied: decorator>=3.0.0 in /usr/local/lib/python3.11/dist-packages (from librosa==0.8.1->BigVGAN==0.0.1) (4.4.2)\n",
            "Collecting resampy>=0.2.2 (from librosa==0.8.1->BigVGAN==0.0.1)\n",
            "  Downloading resampy-0.4.3-py3-none-any.whl.metadata (3.0 kB)\n",
            "Requirement already satisfied: numba>=0.43.0 in /usr/local/lib/python3.11/dist-packages (from librosa==0.8.1->BigVGAN==0.0.1) (0.61.0)\n",
            "Requirement already satisfied: pooch>=1.0 in /usr/local/lib/python3.11/dist-packages (from librosa==0.8.1->BigVGAN==0.0.1) (1.8.2)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from librosa==0.8.1->BigVGAN==0.0.1) (24.2)\n",
            "Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.11/dist-packages (from soundfile->BigVGAN==0.0.1) (1.17.1)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->BigVGAN==0.0.1) (1.3.1)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib->BigVGAN==0.0.1) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib->BigVGAN==0.0.1) (4.55.8)\n",
            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->BigVGAN==0.0.1) (1.4.8)\n",
            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.11/dist-packages (from matplotlib->BigVGAN==0.0.1) (11.1.0)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->BigVGAN==0.0.1) (3.2.1)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.11/dist-packages (from matplotlib->BigVGAN==0.0.1) (2.8.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch->BigVGAN==0.0.1) (3.17.0)\n",
            "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.11/dist-packages (from torch->BigVGAN==0.0.1) (4.12.2)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch->BigVGAN==0.0.1) (3.4.2)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch->BigVGAN==0.0.1) (3.1.5)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch->BigVGAN==0.0.1) (2024.10.0)\n",
            "Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cublas-cu12==12.4.5.8 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cufft-cu12==11.2.1.3 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-curand-cu12==10.3.5.147 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
            "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch->BigVGAN==0.0.1) (2.21.5)\n",
            "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->BigVGAN==0.0.1) (12.4.127)\n",
            "Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch->BigVGAN==0.0.1)\n",
            "  Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
            "Requirement already satisfied: triton==3.1.0 in /usr/local/lib/python3.11/dist-packages (from torch->BigVGAN==0.0.1) (3.1.0)\n",
            "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch->BigVGAN==0.0.1) (1.13.1)\n",
            "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch->BigVGAN==0.0.1) (1.3.0)\n",
            "Requirement already satisfied: pycparser in /usr/local/lib/python3.11/dist-packages (from cffi>=1.0->soundfile->BigVGAN==0.0.1) (2.22)\n",
            "Requirement already satisfied: llvmlite<0.45,>=0.44.0dev0 in /usr/local/lib/python3.11/dist-packages (from numba>=0.43.0->librosa==0.8.1->BigVGAN==0.0.1) (0.44.0)\n",
            "Requirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.11/dist-packages (from pooch>=1.0->librosa==0.8.1->BigVGAN==0.0.1) (4.3.6)\n",
            "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.11/dist-packages (from pooch>=1.0->librosa==0.8.1->BigVGAN==0.0.1) (2.32.3)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.7->matplotlib->BigVGAN==0.0.1) (1.17.0)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn!=0.19.0,>=0.14.0->librosa==0.8.1->BigVGAN==0.0.1) (3.5.0)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch->BigVGAN==0.0.1) (3.0.2)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa==0.8.1->BigVGAN==0.0.1) (3.4.1)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa==0.8.1->BigVGAN==0.0.1) (3.10)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa==0.8.1->BigVGAN==0.0.1) (2.3.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa==0.8.1->BigVGAN==0.0.1) (2025.1.31)\n",
            "Downloading librosa-0.8.1-py3-none-any.whl (203 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m203.8/203.8 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading auraloss-0.4.0-py3-none-any.whl (16 kB)\n",
            "Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m65.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m57.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m46.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m870.6 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m90.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading resampy-0.4.3-py3-none-any.whl (3.1 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m87.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hBuilding wheels for collected packages: BigVGAN, pesq\n",
            "  Building wheel for BigVGAN (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for BigVGAN: filename=BigVGAN-0.0.1-py3-none-any.whl size=22467 sha256=ab54d0940a981390cba2aa632c37917e539f4a4d086b12afa0314165b0cfa5be\n",
            "  Stored in directory: /tmp/pip-ephem-wheel-cache-yw2wzksk/wheels/18/72/eb/fc4f7bbdd6c9f1c26317d0539441375df1598b3c4b4f9b1c97\n",
            "  Building wheel for pesq (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for pesq: filename=pesq-0.0.4-cp311-cp311-linux_x86_64.whl size=275937 sha256=057dc989df9b58fe347d7249a12928108c07b1e89f3229912eb8523137a1e764\n",
            "  Stored in directory: /root/.cache/pip/wheels/ae/f1/23/2698d0bf31eec2b2aa50623b5d93b6206c49c7155d0e31345d\n",
            "Successfully built BigVGAN pesq\n",
            "Installing collected packages: pesq, nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, resampy, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, librosa, auraloss, BigVGAN\n",
            "  Attempting uninstall: nvidia-nvjitlink-cu12\n",
            "    Found existing installation: nvidia-nvjitlink-cu12 12.5.82\n",
            "    Uninstalling nvidia-nvjitlink-cu12-12.5.82:\n",
            "      Successfully uninstalled nvidia-nvjitlink-cu12-12.5.82\n",
            "  Attempting uninstall: nvidia-curand-cu12\n",
            "    Found existing installation: nvidia-curand-cu12 10.3.6.82\n",
            "    Uninstalling nvidia-curand-cu12-10.3.6.82:\n",
            "      Successfully uninstalled nvidia-curand-cu12-10.3.6.82\n",
            "  Attempting uninstall: nvidia-cufft-cu12\n",
            "    Found existing installation: nvidia-cufft-cu12 11.2.3.61\n",
            "    Uninstalling nvidia-cufft-cu12-11.2.3.61:\n",
            "      Successfully uninstalled nvidia-cufft-cu12-11.2.3.61\n",
            "  Attempting uninstall: nvidia-cuda-runtime-cu12\n",
            "    Found existing installation: nvidia-cuda-runtime-cu12 12.5.82\n",
            "    Uninstalling nvidia-cuda-runtime-cu12-12.5.82:\n",
            "      Successfully uninstalled nvidia-cuda-runtime-cu12-12.5.82\n",
            "  Attempting uninstall: nvidia-cuda-nvrtc-cu12\n",
            "    Found existing installation: nvidia-cuda-nvrtc-cu12 12.5.82\n",
            "    Uninstalling nvidia-cuda-nvrtc-cu12-12.5.82:\n",
            "      Successfully uninstalled nvidia-cuda-nvrtc-cu12-12.5.82\n",
            "  Attempting uninstall: nvidia-cuda-cupti-cu12\n",
            "    Found existing installation: nvidia-cuda-cupti-cu12 12.5.82\n",
            "    Uninstalling nvidia-cuda-cupti-cu12-12.5.82:\n",
            "      Successfully uninstalled nvidia-cuda-cupti-cu12-12.5.82\n",
            "  Attempting uninstall: nvidia-cublas-cu12\n",
            "    Found existing installation: nvidia-cublas-cu12 12.5.3.2\n",
            "    Uninstalling nvidia-cublas-cu12-12.5.3.2:\n",
            "      Successfully uninstalled nvidia-cublas-cu12-12.5.3.2\n",
            "  Attempting uninstall: nvidia-cusparse-cu12\n",
            "    Found existing installation: nvidia-cusparse-cu12 12.5.1.3\n",
            "    Uninstalling nvidia-cusparse-cu12-12.5.1.3:\n",
            "      Successfully uninstalled nvidia-cusparse-cu12-12.5.1.3\n",
            "  Attempting uninstall: nvidia-cudnn-cu12\n",
            "    Found existing installation: nvidia-cudnn-cu12 9.3.0.75\n",
            "    Uninstalling nvidia-cudnn-cu12-9.3.0.75:\n",
            "      Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75\n",
            "  Attempting uninstall: nvidia-cusolver-cu12\n",
            "    Found existing installation: nvidia-cusolver-cu12 11.6.3.83\n",
            "    Uninstalling nvidia-cusolver-cu12-11.6.3.83:\n",
            "      Successfully uninstalled nvidia-cusolver-cu12-11.6.3.83\n",
            "  Attempting uninstall: librosa\n",
            "    Found existing installation: librosa 0.10.2.post1\n",
            "    Uninstalling librosa-0.10.2.post1:\n",
            "      Successfully uninstalled librosa-0.10.2.post1\n",
            "Successfully installed BigVGAN-0.0.1 auraloss-0.4.0 librosa-0.8.1 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127 pesq-0.0.4 resampy-0.4.3\n"
          ]
        }
      ],
      "source": [
        "!git clone https://github.com/152334H/tortoise-tts-fast\n",
        "%cd tortoise-tts-fast\n",
        "!pip3 install -r requirements.txt --no-deps\n",
        "!pip3 install -e .\n",
        "!pip3 install git+https://github.com/152334H/BigVGAN.git"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zRW4p3ftjZ3Y"
      },
      "source": [
        "## **Restart the runtime!**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Gen09NM4hONQ"
      },
      "outputs": [],
      "source": [
        "#@title # Setup\n",
        "# Imports used through the rest of the notebook.\n",
        "import torch\n",
        "import torchaudio\n",
        "import torch.nn as nn\n",
        "import torch.nn.functional as F\n",
        "\n",
        "import IPython\n",
        "\n",
        "from tortoise.api import TextToSpeech\n",
        "from tortoise.utils.audio import load_audio, load_voice, load_voices\n",
        "\n",
        "# This will download all the models used by Tortoise from the HuggingFace hub.\n",
        "tts = TextToSpeech()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "bt_aoxONjfL2"
      },
      "outputs": [],
      "source": [
        "# This is the text that will be spoken.\n",
        "text = \"Joining two modalities results in a surprising increase in generalization! What would happen if we combined them all?\" #@param {type:\"string\"}\n",
        "#@markdown Show code for multiline text input\n",
        "# Here's something for the poetically inclined.. (set text=)\n",
        "\"\"\"\n",
        "Then took the other, as just as fair,\n",
        "And having perhaps the better claim,\n",
        "Because it was grassy and wanted wear;\n",
        "Though as for that the passing there\n",
        "Had worn them really about the same,\"\"\"\n",
        "\n",
        "# Pick a \"preset mode\" to determine quality. Options: {\"ultra_fast\", \"fast\" (default), \"standard\", \"high_quality\"}. See docs in api.py\n",
        "preset = \"ultra_fast\" #@param [\"ultra_fast\", \"fast\", \"standard\", \"high_quality\"]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "SSleVnRAiEE2"
      },
      "outputs": [],
      "source": [
        "#@markdown Tortoise will attempt to mimic voices you provide. It comes pre-packaged\n",
        "#@markdown with some voices you might recognize.\n",
        "\n",
        "#@markdown Let's list all the voices available. These are just some random clips I've gathered\n",
        "#@markdown from the internet as well as a few voices from the training dataset.\n",
        "#@markdown Feel free to add your own clips to the voices/ folder.\n",
        "%cd tortoise-tts-fast\n",
        "%ls tortoise/voices\n",
        "import IPython\n",
        "IPython.display.Audio(filename='tortoise/voices/tom/1.wav')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "cellView": "form",
        "id": "KEXOKjIvn6NW"
      },
      "outputs": [],
      "source": [
        "#@markdown Pick one of the voices from the output above\n",
        "voice = 'train_dotrice' #@param {type:\"string\"}\n",
        "\n",
        "#@markdown Load it and send it through Tortoise.\n",
        "voice_samples, conditioning_latents = load_voice(voice)\n",
        "gen = tts.tts_with_preset(text, voice_samples=voice_samples, conditioning_latents=conditioning_latents,\n",
        "                          preset=preset)\n",
        "torchaudio.save('generated.wav', gen.squeeze(0).cpu(), 24000)\n",
        "IPython.display.Audio('generated.wav')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "16Xs2SSC3BXa"
      },
      "outputs": [],
      "source": [
        "#@markdown Tortoise can also generate speech using a random voice. The voice changes each time you execute this!\n",
        "#@markdown (Note: random voices can be prone to strange utterances)\n",
        "gen = tts.tts_with_preset(text, voice_samples=None, conditioning_latents=None, preset=preset)\n",
        "torchaudio.save('generated.wav', gen.squeeze(0).cpu(), 24000)\n",
        "IPython.display.Audio('generated.wav')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "VQgw3KeV8Yqb"
      },
      "outputs": [],
      "source": [
        "#@markdown Optionally, upload use your own voice by running the next two cells. I recommend\n",
        "#@markdown you upload at least 2 audio clips. They must be a WAV file, 6-10 seconds long.\n",
        "CUSTOM_VOICE_NAME = \"custom\"\n",
        "\n",
        "import os\n",
        "from google.colab import files\n",
        "\n",
        "custom_voice_folder = f\"tortoise/voices/{CUSTOM_VOICE_NAME}\"\n",
        "os.makedirs(custom_voice_folder)\n",
        "for i, file_data in enumerate(files.upload().values()):\n",
        "  with open(os.path.join(custom_voice_folder, f'{i}.wav'), 'wb') as f:\n",
        "    f.write(file_data)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "jJnJwv3R9uWT"
      },
      "outputs": [],
      "source": [
        "# Generate speech with the custotm voice.\n",
        "voice_samples, conditioning_latents = load_voice(CUSTOM_VOICE_NAME)\n",
        "gen = tts.tts_with_preset(text, voice_samples=voice_samples, conditioning_latents=conditioning_latents,\n",
        "                          preset=preset)\n",
        "torchaudio.save(f'generated-{CUSTOM_VOICE_NAME}.wav', gen.squeeze(0).cpu(), 24000)\n",
        "IPython.display.Audio(f'generated-{CUSTOM_VOICE_NAME}.wav')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "fYTk8KUezUr5"
      },
      "outputs": [],
      "source": [
        "# You can also combine conditioning voices. Combining voices produces a new voice\n",
        "# with traits from all the parents.\n",
        "#\n",
        "# Lets see what it would sound like if Picard and Kirk had a kid with a penchant for philosophy:\n",
        "voice_samples, conditioning_latents = load_voices(['pat', 'william'])\n",
        "\n",
        "gen = tts.tts_with_preset(\"They used to say that if man was meant to fly, he’d have wings. But he did fly. He discovered he had to.\",\n",
        "                          voice_samples=voice_samples, conditioning_latents=conditioning_latents,\n",
        "                          preset=preset)\n",
        "torchaudio.save('captain_kirkard.wav', gen.squeeze(0).cpu(), 24000)\n",
        "IPython.display.Audio('captain_kirkard.wav')"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.9.16"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}