Persian-G2P-Tools-Benchmark/benchmarking-scripts/Benchmark_eSpeak_NG.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "collapsed_sections": [
        "ABgLYF9R8viP",
        "EOZGZa2lMfPe",
        "AdU8VMTIOWLZ",
        "XhbCA2tkR45b",
        "XjAPkfq7SF87",
        "f4NqCjr1FxVg",
        "oBgNtpFQDwku",
        "JGEUIrbi9kNH"
      ]
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "! pip install hazm==0.10.0"
      ],
      "metadata": {
        "id": "KoaoU_iCNhGt",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "09c602ac-7664-4e3f-8bcb-32e7337e24ee"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting hazm==0.10.0\n",
            "  Downloading hazm-0.10.0-py3-none-any.whl.metadata (11 kB)\n",
            "Collecting fasttext-wheel<0.10.0,>=0.9.2 (from hazm==0.10.0)\n",
            "  Downloading fasttext_wheel-0.9.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (16 kB)\n",
            "Collecting flashtext<3.0,>=2.7 (from hazm==0.10.0)\n",
            "  Downloading flashtext-2.7.tar.gz (14 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting gensim<5.0.0,>=4.3.1 (from hazm==0.10.0)\n",
            "  Downloading gensim-4.3.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (8.1 kB)\n",
            "Requirement already satisfied: nltk<4.0.0,>=3.8.1 in /usr/local/lib/python3.11/dist-packages (from hazm==0.10.0) (3.9.1)\n",
            "Collecting numpy==1.24.3 (from hazm==0.10.0)\n",
            "  Downloading numpy-1.24.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.6 kB)\n",
            "Collecting python-crfsuite<0.10.0,>=0.9.9 (from hazm==0.10.0)\n",
            "  Downloading python_crfsuite-0.9.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.3 kB)\n",
            "Requirement already satisfied: scikit-learn<2.0.0,>=1.2.2 in /usr/local/lib/python3.11/dist-packages (from hazm==0.10.0) (1.6.1)\n",
            "Collecting pybind11>=2.2 (from fasttext-wheel<0.10.0,>=0.9.2->hazm==0.10.0)\n",
            "  Downloading pybind11-2.13.6-py3-none-any.whl.metadata (9.5 kB)\n",
            "Requirement already satisfied: setuptools>=0.7.0 in /usr/local/lib/python3.11/dist-packages (from fasttext-wheel<0.10.0,>=0.9.2->hazm==0.10.0) (75.2.0)\n",
            "Collecting scipy<1.14.0,>=1.7.0 (from gensim<5.0.0,>=4.3.1->hazm==0.10.0)\n",
            "  Downloading scipy-1.13.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.6/60.6 kB\u001b[0m \u001b[31m2.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: smart-open>=1.8.1 in /usr/local/lib/python3.11/dist-packages (from gensim<5.0.0,>=4.3.1->hazm==0.10.0) (7.1.0)\n",
            "Requirement already satisfied: click in /usr/local/lib/python3.11/dist-packages (from nltk<4.0.0,>=3.8.1->hazm==0.10.0) (8.1.8)\n",
            "Requirement already satisfied: joblib in /usr/local/lib/python3.11/dist-packages (from nltk<4.0.0,>=3.8.1->hazm==0.10.0) (1.4.2)\n",
            "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.11/dist-packages (from nltk<4.0.0,>=3.8.1->hazm==0.10.0) (2024.11.6)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from nltk<4.0.0,>=3.8.1->hazm==0.10.0) (4.67.1)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn<2.0.0,>=1.2.2->hazm==0.10.0) (3.6.0)\n",
            "Requirement already satisfied: wrapt in /usr/local/lib/python3.11/dist-packages (from smart-open>=1.8.1->gensim<5.0.0,>=4.3.1->hazm==0.10.0) (1.17.2)\n",
            "Downloading hazm-0.10.0-py3-none-any.whl (892 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m892.6/892.6 kB\u001b[0m \u001b[31m24.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading numpy-1.24.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.3 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.3/17.3 MB\u001b[0m \u001b[31m64.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading fasttext_wheel-0.9.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.4 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.4/4.4 MB\u001b[0m \u001b[31m28.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading gensim-4.3.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (26.7 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m26.7/26.7 MB\u001b[0m \u001b[31m42.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading python_crfsuite-0.9.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m40.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading pybind11-2.13.6-py3-none-any.whl (243 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m243.3/243.3 kB\u001b[0m \u001b[31m16.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading scipy-1.13.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (38.6 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.6/38.6 MB\u001b[0m \u001b[31m13.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hBuilding wheels for collected packages: flashtext\n",
            "  Building wheel for flashtext (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for flashtext: filename=flashtext-2.7-py2.py3-none-any.whl size=9300 sha256=181e31aa2933b81d1d4b23e453d93e170ac703c16bd7cb21b77b97ed66a93296\n",
            "  Stored in directory: /root/.cache/pip/wheels/49/20/47/f03dfa8a7239c54cbc44ff7389eefbf888d2c1873edaaec888\n",
            "Successfully built flashtext\n",
            "Installing collected packages: flashtext, python-crfsuite, pybind11, numpy, scipy, fasttext-wheel, gensim, hazm\n",
            "  Attempting uninstall: numpy\n",
            "    Found existing installation: numpy 2.0.2\n",
            "    Uninstalling numpy-2.0.2:\n",
            "      Successfully uninstalled numpy-2.0.2\n",
            "  Attempting uninstall: scipy\n",
            "    Found existing installation: scipy 1.15.2\n",
            "    Uninstalling scipy-1.15.2:\n",
            "      Successfully uninstalled scipy-1.15.2\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "blosc2 3.3.2 requires numpy>=1.26, but you have numpy 1.24.3 which is incompatible.\n",
            "thinc 8.3.6 requires numpy<3.0.0,>=2.0.0, but you have numpy 1.24.3 which is incompatible.\n",
            "treescope 0.1.9 requires numpy>=1.25.2, but you have numpy 1.24.3 which is incompatible.\n",
            "pymc 5.22.0 requires numpy>=1.25.0, but you have numpy 1.24.3 which is incompatible.\n",
            "albumentations 2.0.6 requires numpy>=1.24.4, but you have numpy 1.24.3 which is incompatible.\n",
            "albucore 0.0.24 requires numpy>=1.24.4, but you have numpy 1.24.3 which is incompatible.\n",
            "tensorflow 2.18.0 requires numpy<2.1.0,>=1.26.0, but you have numpy 1.24.3 which is incompatible.\n",
            "jax 0.5.2 requires numpy>=1.25, but you have numpy 1.24.3 which is incompatible.\n",
            "jaxlib 0.5.1 requires numpy>=1.25, but you have numpy 1.24.3 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed fasttext-wheel-0.9.2 flashtext-2.7 gensim-4.3.3 hazm-0.10.0 numpy-1.24.3 pybind11-2.13.6 python-crfsuite-0.9.11 scipy-1.13.1\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "numpy"
                ]
              },
              "id": "144c92821f314ca8b8454fbffa93554f"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!sudo apt-get install espeak-ng"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Bn--f9NnAWx8",
        "outputId": "6bf40904-ab6f-4271-de47-155f6624993c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Reading package lists... Done\n",
            "Building dependency tree... Done\n",
            "Reading state information... Done\n",
            "The following additional packages will be installed:\n",
            "  espeak-ng-data libespeak-ng1 libpcaudio0 libsonic0\n",
            "The following NEW packages will be installed:\n",
            "  espeak-ng espeak-ng-data libespeak-ng1 libpcaudio0 libsonic0\n",
            "0 upgraded, 5 newly installed, 0 to remove and 34 not upgraded.\n",
            "Need to get 4,526 kB of archives.\n",
            "After this operation, 11.9 MB of additional disk space will be used.\n",
            "Get:1 http://archive.ubuntu.com/ubuntu jammy/main amd64 libpcaudio0 amd64 1.1-6build2 [8,956 B]\n",
            "Get:2 http://archive.ubuntu.com/ubuntu jammy/main amd64 libsonic0 amd64 0.2.0-11build1 [10.3 kB]\n",
            "Get:3 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 espeak-ng-data amd64 1.50+dfsg-10ubuntu0.1 [3,956 kB]\n",
            "Get:4 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 libespeak-ng1 amd64 1.50+dfsg-10ubuntu0.1 [207 kB]\n",
            "Get:5 http://archive.ubuntu.com/ubuntu jammy-updates/universe amd64 espeak-ng amd64 1.50+dfsg-10ubuntu0.1 [343 kB]\n",
            "Fetched 4,526 kB in 1s (4,828 kB/s)\n",
            "debconf: unable to initialize frontend: Dialog\n",
            "debconf: (No usable dialog-like program is installed, so the dialog based frontend cannot be used. at /usr/share/perl5/Debconf/FrontEnd/Dialog.pm line 78, <> line 5.)\n",
            "debconf: falling back to frontend: Readline\n",
            "debconf: unable to initialize frontend: Readline\n",
            "debconf: (This frontend requires a controlling tty.)\n",
            "debconf: falling back to frontend: Teletype\n",
            "dpkg-preconfigure: unable to re-open stdin: \n",
            "Selecting previously unselected package libpcaudio0:amd64.\n",
            "(Reading database ... 126102 files and directories currently installed.)\n",
            "Preparing to unpack .../libpcaudio0_1.1-6build2_amd64.deb ...\n",
            "Unpacking libpcaudio0:amd64 (1.1-6build2) ...\n",
            "Selecting previously unselected package libsonic0:amd64.\n",
            "Preparing to unpack .../libsonic0_0.2.0-11build1_amd64.deb ...\n",
            "Unpacking libsonic0:amd64 (0.2.0-11build1) ...\n",
            "Selecting previously unselected package espeak-ng-data:amd64.\n",
            "Preparing to unpack .../espeak-ng-data_1.50+dfsg-10ubuntu0.1_amd64.deb ...\n",
            "Unpacking espeak-ng-data:amd64 (1.50+dfsg-10ubuntu0.1) ...\n",
            "Selecting previously unselected package libespeak-ng1:amd64.\n",
            "Preparing to unpack .../libespeak-ng1_1.50+dfsg-10ubuntu0.1_amd64.deb ...\n",
            "Unpacking libespeak-ng1:amd64 (1.50+dfsg-10ubuntu0.1) ...\n",
            "Selecting previously unselected package espeak-ng.\n",
            "Preparing to unpack .../espeak-ng_1.50+dfsg-10ubuntu0.1_amd64.deb ...\n",
            "Unpacking espeak-ng (1.50+dfsg-10ubuntu0.1) ...\n",
            "Setting up libpcaudio0:amd64 (1.1-6build2) ...\n",
            "Setting up libsonic0:amd64 (0.2.0-11build1) ...\n",
            "Setting up espeak-ng-data:amd64 (1.50+dfsg-10ubuntu0.1) ...\n",
            "Setting up libespeak-ng1:amd64 (1.50+dfsg-10ubuntu0.1) ...\n",
            "Setting up espeak-ng (1.50+dfsg-10ubuntu0.1) ...\n",
            "Processing triggers for man-db (2.10.2-1) ...\n",
            "Processing triggers for libc-bin (2.35-0ubuntu3.8) ...\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_0.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libumf.so.0 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libur_adapter_opencl.so.0 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libhwloc.so.15 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libur_adapter_level_zero.so.0 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc.so.2 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtcm_debug.so.1 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtcm.so.1 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libur_loader.so.0 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_5.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc_proxy.so.2 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbb.so.12 is not a symbolic link\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install jiwer"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jBaEWi0m5uNj",
        "outputId": "07c1ebc8-9b5d-45d2-946f-6cb0217cde07"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting jiwer\n",
            "  Downloading jiwer-3.1.0-py3-none-any.whl.metadata (2.6 kB)\n",
            "Requirement already satisfied: click>=8.1.8 in /usr/local/lib/python3.11/dist-packages (from jiwer) (8.1.8)\n",
            "Collecting rapidfuzz>=3.9.7 (from jiwer)\n",
            "  Downloading rapidfuzz-3.13.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
            "Downloading jiwer-3.1.0-py3-none-any.whl (22 kB)\n",
            "Downloading rapidfuzz-3.13.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.1 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m38.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hInstalling collected packages: rapidfuzz, jiwer\n",
            "Successfully installed jiwer-3.1.0 rapidfuzz-3.13.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import re\n",
        "from jiwer import cer"
      ],
      "metadata": {
        "id": "R5exL3ah5yoA"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def transform_text(text):\n",
        "    \"\"\"\n",
        "    Transform text according to specified rules:\n",
        "    1. Apply phoneme substitutions\n",
        "    2. Add question marks before vowels at word boundaries\n",
        "    3. Remove specific symbols\n",
        "\n",
        "    Args:\n",
        "        text (str): Input text to transform\n",
        "\n",
        "    Returns:\n",
        "        str: Transformed text\n",
        "    \"\"\"\n",
        "    # Define the consonant and vowel regex patterns\n",
        "    consonants = ['q', 'r', 't', 'y', 'p', 's', 'd', 'f', 'g', 'h', 'j', 'k', 'l',\n",
        "                 'z', 'x', 'c', 'v', 'b', 'n', 'm', 'Q', 'R', 'T', 'Y', 'P', 'S',\n",
        "                 'D', 'F', 'G', 'H', 'J', 'K', 'L', 'Z', 'X', 'C', 'V', 'B', 'N', 'M']\n",
        "    vowels = ['a', 'A', 'e', 'i', 'u', 'o']\n",
        "\n",
        "    consonants_regex = '(?=' + '|'.join(consonants) + ')'\n",
        "    vowels_regex = '(?=' + '|'.join(vowels) + ')'\n",
        "\n",
        "    # Step 1: Apply phoneme substitutions\n",
        "    substitutions = {\n",
        "        'tS': 'C',\n",
        "        'j': 'y',\n",
        "        'dZ': 'j',\n",
        "        'R': 'r',\n",
        "        'q1': 'q'\n",
        "    }\n",
        "\n",
        "    for old, new in substitutions.items():\n",
        "        text = text.replace(old, new)\n",
        "\n",
        "    # Step 3: Remove specific symbols\n",
        "    symbols_to_remove = [\"'\", \":\", \",\"]\n",
        "    for symbol in symbols_to_remove:\n",
        "        text = text.replace(symbol, '')\n",
        "\n",
        "    # Step 2: Add question marks before vowels at word boundaries\n",
        "    text = re.sub(rf'([^\\w\\-]|^){vowels_regex}', r'\\1?', text)\n",
        "\n",
        "    return text\n"
      ],
      "metadata": {
        "id": "kwOHbGP9FWJs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import subprocess\n",
        "\n",
        "def text_to_phonemes(text, voice='fa', ipa=False, tie_character=None, separator=None):\n",
        "    \"\"\"\n",
        "    Convert text to phonemes using espeak-ng.\n",
        "\n",
        "    Args:\n",
        "        text (str): Input text to convert to phonemes\n",
        "        voice (str, optional): Voice to use (e.g., 'en-us', 'fr'). Defaults to None (default voice).\n",
        "        ipa (bool, optional): Use International Phonetic Alphabet. Defaults to False.\n",
        "        tie_character (str, optional): Character to join multi-letter phonemes. Defaults to None.\n",
        "        separator (str, optional): Character to separate phonemes. Defaults to None.\n",
        "\n",
        "    Returns:\n",
        "        str: Phoneme representation of the input text\n",
        "    \"\"\"\n",
        "    command = ['espeak-ng', '-q', '-x']  # -q for quiet, -x for phoneme output\n",
        "\n",
        "    if voice:\n",
        "        command.extend(['-v', voice])\n",
        "    if ipa:\n",
        "        command.append('--ipa')\n",
        "    if tie_character:\n",
        "        command.extend(['--tie', tie_character])\n",
        "    if separator:\n",
        "        command.extend(['--sep', separator])\n",
        "\n",
        "    # Add the text to process\n",
        "    command.append(text)\n",
        "\n",
        "    try:\n",
        "        result = subprocess.run(\n",
        "            command,\n",
        "            check=True,\n",
        "            stdout=subprocess.PIPE,\n",
        "            stderr=subprocess.PIPE,\n",
        "            text=True\n",
        "        )\n",
        "        phoneme_seq = result.stdout.strip()\n",
        "        transformed_phoneme_seq = transform_text(phoneme_seq)\n",
        "        return transformed_phoneme_seq\n",
        "    except subprocess.CalledProcessError as e:\n",
        "        raise RuntimeError(f\"espeak-ng failed: {e.stderr}\") from e\n",
        "    except FileNotFoundError as e:\n",
        "        raise RuntimeError(\"espeak-ng is not installed or not in PATH\") from e"
      ],
      "metadata": {
        "id": "E8V116dgBOci"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "XjAPkfq7SF87"
      },
      "source": [
        "## Get Evaluation Data"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!wget https://huggingface.co/datasets/MahtaFetrat/SentenceBench/raw/main/SentenceBench.csv"
      ],
      "metadata": {
        "id": "qwCG0jX-88nQ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1564bd7a-c5bd-46a3-fa45-6532fdfc6750"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2025-05-10 20:59:44--  https://huggingface.co/datasets/MahtaFetrat/SentenceBench/raw/main/SentenceBench.csv\n",
            "Resolving huggingface.co (huggingface.co)... 3.163.189.90, 3.163.189.37, 3.163.189.74, ...\n",
            "Connecting to huggingface.co (huggingface.co)|3.163.189.90|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 56026 (55K) [text/plain]\n",
            "Saving to: ‘SentenceBench.csv’\n",
            "\n",
            "\rSentenceBench.csv     0%[                    ]       0  --.-KB/s               \rSentenceBench.csv   100%[===================>]  54.71K  --.-KB/s    in 0.008s  \n",
            "\n",
            "2025-05-10 20:59:44 (6.50 MB/s) - ‘SentenceBench.csv’ saved [56026/56026]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "sentence_bench = pd.read_csv('SentenceBench.csv')"
      ],
      "metadata": {
        "id": "hJO-UAPDQvcb"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "sentence_bench.head(3)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 143
        },
        "id": "qlYbrnUa9LAN",
        "outputId": "ce9a29ac-c6a4-4c8a-b829-97ead674af09"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     dataset                              grapheme  \\\n",
              "0  homograph                  من قدر تو را می‌دانم   \n",
              "1  homograph  از قضای الهی به قدر الهی پناه می‌برم   \n",
              "2  homograph                به دست و صورتم کرم زدم   \n",
              "\n",
              "                                             phoneme homograph word  \\\n",
              "0                          man qadr-e to rA mi-dAnam            قدر   \n",
              "1  ?az qazAy ?elAhi be qadar-e ?elAhi panAh mi-baram            قدر   \n",
              "2                      be dast-o suratam kerem zadam            کرم   \n",
              "\n",
              "  pronunciation  \n",
              "0          qadr  \n",
              "1         qadar  \n",
              "2         kerem  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-0f3443f9-2364-4c95-ad21-e297d127156b\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>dataset</th>\n",
              "      <th>grapheme</th>\n",
              "      <th>phoneme</th>\n",
              "      <th>homograph word</th>\n",
              "      <th>pronunciation</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>homograph</td>\n",
              "      <td>من قدر تو را می‌دانم</td>\n",
              "      <td>man qadr-e to rA mi-dAnam</td>\n",
              "      <td>قدر</td>\n",
              "      <td>qadr</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>homograph</td>\n",
              "      <td>از قضای الهی به قدر الهی پناه می‌برم</td>\n",
              "      <td>?az qazAy ?elAhi be qadar-e ?elAhi panAh mi-baram</td>\n",
              "      <td>قدر</td>\n",
              "      <td>qadar</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>homograph</td>\n",
              "      <td>به دست و صورتم کرم زدم</td>\n",
              "      <td>be dast-o suratam kerem zadam</td>\n",
              "      <td>کرم</td>\n",
              "      <td>kerem</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0f3443f9-2364-4c95-ad21-e297d127156b')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-0f3443f9-2364-4c95-ad21-e297d127156b button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-0f3443f9-2364-4c95-ad21-e297d127156b');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-eed350e1-3b88-4a95-a1a7-ede78c415da5\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-eed350e1-3b88-4a95-a1a7-ede78c415da5')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-eed350e1-3b88-4a95-a1a7-ede78c415da5 button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "sentence_bench",
              "summary": "{\n  \"name\": \"sentence_bench\",\n  \"rows\": 400,\n  \"fields\": [\n    {\n      \"column\": \"dataset\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"homograph\",\n          \"mana-tts\",\n          \"commonvoice\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"grapheme\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 400,\n        \"samples\": [\n          \"\\u0622\\u06cc\\u0627 \\u0628\\u0627\\u06cc\\u062f \\u062d\\u0642\\u06cc\\u0642\\u062a \\u0631\\u0627 \\u0628\\u0647 \\u0622\\u0646\\u200c\\u0647\\u0627 \\u0628\\u06af\\u0648\\u06cc\\u06cc\\u0645\\u061f\",\n          \"\\u06a9\\u0647 \\u067e\\u06cc\\u0634 \\u0627\\u0632 \\u0627\\u0646\\u0642\\u0644\\u0627\\u0628 \\u0628\\u0647 \\u062e\\u0648\\u0627\\u0628\\u06af\\u0627\\u0647 \\u062f\\u062e\\u062a\\u0631\\u0627\\u0646 \\u0648 \\u0632\\u0646\\u0627\\u0646 \\u0646\\u0627\\u0628\\u06cc\\u0646\\u0627 \\u0627\\u062e\\u062a\\u0635\\u0627\\u0635\\u200c\\u06cc\\u0627\\u0641\\u062a\\u0647 \\u0628\\u0648\\u062f. \\u0627\\u063a\\u0644\\u0628 \\u0632\\u0646\\u0627\\u0646\\u06cc \\u06a9\\u0647 \\u062f\\u0631 \\u0627\\u06cc\\u0646 \\u062e\\u0648\\u0627\\u0628\\u06af\\u0627\\u0647 \\u0632\\u0646\\u062f\\u06af\\u06cc \\u0645\\u06cc\\u200c\\u06a9\\u0631\\u062f\\u0646\\u062f\\u060c \",\n          \"\\u062f\\u0648\\u062f \\u0648 \\u0645\\u0647 \\u063a\\u0644\\u06cc\\u0638\\u06cc \\u062f\\u0631 \\u0645\\u062d\\u06cc\\u0637 \\u067e\\u06cc\\u0686\\u06cc\\u062f\\u0647 \\u0628\\u0648\\u062f\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"phoneme\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 400,\n        \"samples\": [\n          \"?AyA bAyad haqiqat rA be ?AnhA beguyim\\u061f\",\n          \"ke piS ?az ?enqelAb be xAbgAh-e doxtarAn va zanAn-e nAbinA ?extesAsyAfte bud ?aqlab-e zanAni ke dar ?in xAbgAh zendegi mikardand\",\n          \"dud-o meh-e qalizi dar mohit piCide bud\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"homograph word\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 101,\n        \"samples\": [\n          \"\\u06af\\u0631\\u06cc\\u0645\",\n          \"\\u0633\\u0628\\u06a9\\u06cc\",\n          \"\\u06a9\\u0645\\u06cc\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"pronunciation\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 210,\n        \"samples\": [\n          \"darham\",\n          \"Sum\",\n          \"moSk\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wDV7ysXf2b_H"
      },
      "source": [
        "### Get ManaTTS"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TcL5ZLvSSnVB",
        "outputId": "66b99ca9-442a-46c9-81d6-49cf7a35d08a"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[('در این نوشته بنا داریم با یک ابزار ساده و مکانیکی افزایش بینایی برای افراد کم\\u200cبینا ',\n",
              "  'dar ?in neveSte banA dArim bA yek ?abzAr-e sAde va mekAniki-ye ?afzAyeS-e binAyi barAye ?afrAd-e kam\\u200cbinA '),\n",
              " ('به نام بی\\u200cوپتیک یا عدسی دورنما آشنا شویم. ',\n",
              "  'be nAm-e biyoptik yA ?adasi-ye durnamA ?ASnA Savim'),\n",
              " ('دراین\\u200cصورت، انجام خودارزیابی و ارائه بازخورد بر عهده خودتان است. ',\n",
              "  'dar ?in surat ?anjAm-e xod?arzyAbi va ?erA?e-ye bAzxord bar ?ohde-ye xodetAn ?ast ')]"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ],
      "source": [
        "filtered_rows = sentence_bench[sentence_bench['dataset'] == 'mana-tts'][['grapheme', 'phoneme']]\n",
        "\n",
        "# Convert to a list of tuples\n",
        "mana_evaluation_data = list(filtered_rows.itertuples(index=False, name=None))\n",
        "\n",
        "mana_evaluation_data[:3]"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Jjacw9Mp2eoX"
      },
      "source": [
        "### Get CommonVoice"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "-yQnqCGw26sk",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7f587b1d-f55c-41e9-d4ff-59a381a7e4cd"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[('در اکثر شهرها، مرکزی برای خرید دوچرخه وجود دارد.',\n",
              "  'dar ?aksar-e Sahr-hA, markazi barAye xarid-e  doCarxe vojud dArad.'),\n",
              " ('پس از مدرسه کودکان به سوی خانه جست و خیز کردند.',\n",
              "  'pas ?az madrese kudakAn be suye xAne jast-o-xiz kardand.'),\n",
              " ('شما نگران زن و بچه این نباش.', 'SomA negarAn-e zan-o-baCCe-ye ?in nabAS.')]"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ],
      "source": [
        "filtered_rows = sentence_bench[sentence_bench['dataset'] == 'commonvoice'][['grapheme', 'phoneme']]\n",
        "\n",
        "# Convert to a list of tuples\n",
        "commonvoice_evaluation_data = list(filtered_rows.itertuples(index=False, name=None))\n",
        "\n",
        "commonvoice_evaluation_data[:3]"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ciSPyhRc3Rvo"
      },
      "source": [
        "### Get Homograph"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "XlFc5JbN3Rvz",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "fb6b313f-3d1b-4110-9a11-230c07d07c3d"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[('من قدر تو را می\\u200cدانم', 'man qadr-e to rA mi-dAnam', 'قدر', 'qadr'),\n",
              " ('از قضای الهی به قدر الهی پناه می\\u200cبرم',\n",
              "  '?az qazAy ?elAhi be qadar-e ?elAhi panAh mi-baram',\n",
              "  'قدر',\n",
              "  'qadar'),\n",
              " ('به دست و صورتم کرم زدم', 'be dast-o suratam kerem zadam', 'کرم', 'kerem')]"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ],
      "source": [
        "filtered_rows = sentence_bench[sentence_bench['dataset'] == 'homograph'][['grapheme', 'phoneme', 'homograph word',\t'pronunciation']]\n",
        "\n",
        "# Convert to a list of tuples\n",
        "homograph_evaluation_data = list(filtered_rows.itertuples(index=False, name=None))\n",
        "\n",
        "homograph_evaluation_data[:3]"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "R6PE5ds45TPr"
      },
      "source": [
        "# Evaluate Method Outputs"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "y73zFlRGIbt9"
      },
      "source": [
        "## PER Evaluation"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ItuviO3w5Vzv"
      },
      "outputs": [],
      "source": [
        "def remove_non_word_chars(text):\n",
        "    pattern = r'[^\\w\\s\\?]'\n",
        "    cleaned_text = re.sub(pattern, '', text)\n",
        "    cleaned_text = re.sub('_', '', text)\n",
        "    return cleaned_text"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "syQCurXu51TO"
      },
      "outputs": [],
      "source": [
        "def remove_white_spaces(text):\n",
        "    cleaned_text = re.sub(r'\\s+', ' ', text)\n",
        "    return cleaned_text.strip()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "V7APkVM053RP"
      },
      "outputs": [],
      "source": [
        "def get_word_only_text(text):\n",
        "  word_only_text = remove_non_word_chars(text)\n",
        "  extra_space_removed_text = remove_white_spaces(word_only_text)\n",
        "\n",
        "  return extra_space_removed_text"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ROomKSao57vy"
      },
      "outputs": [],
      "source": [
        "def get_texts_cer(reference, model_output):\n",
        "  # Preprocess input texts to only contain word characters\n",
        "  word_only_reference = get_word_only_text(reference)\n",
        "  word_only_output = get_word_only_text(model_output)\n",
        "\n",
        "  # Return +infinity for CER if any of the texts is empty\n",
        "  if not word_only_reference.strip() or not word_only_output.strip():\n",
        "    return float('inf')\n",
        "\n",
        "  return cer(word_only_reference, word_only_output)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "4vHLUjp48hc3"
      },
      "outputs": [],
      "source": [
        "def get_avg_cer_of_method(method_outputs, references):\n",
        "  cers = []\n",
        "  for idx, o in enumerate(method_outputs):\n",
        "    cer = get_texts_cer(o.replace('-', ''), references[idx][1].replace('-', ''))\n",
        "    if cer != float('inf'):\n",
        "      cers.append(cer)\n",
        "\n",
        "  return sum(cers) / len(cers)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "oBgNtpFQDwku"
      },
      "source": [
        "## Homograph Evaluation"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "J445ULEvEEDn"
      },
      "outputs": [],
      "source": [
        "def get_homograph_performance(outputs, references):\n",
        "  corrects = 0\n",
        "  total = 0\n",
        "\n",
        "  for idx, (g, p, homograph, right) in enumerate(references):\n",
        "    if homograph != '':\n",
        "      total += 1\n",
        "      if right in outputs[idx]:\n",
        "        corrects += 1\n",
        "\n",
        "  return corrects / total"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JGEUIrbi9kNH"
      },
      "source": [
        "# Full bench"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "fGzQvL8V9mln"
      },
      "outputs": [],
      "source": [
        "benchmark = []\n",
        "\n",
        "for g, p in mana_evaluation_data:\n",
        "  benchmark.append((g, p, '', ''))\n",
        "\n",
        "for g, p in commonvoice_evaluation_data:\n",
        "  benchmark.append((g, p, '', ''))\n",
        "\n",
        "for g, p, w, r in homograph_evaluation_data:\n",
        "  benchmark.append((g, p, w, r))\n",
        "\n",
        "benchmark = benchmark[:400]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "4jlXFt8tCPWB"
      },
      "outputs": [],
      "source": [
        "def print_all_metrics(predictions):\n",
        "  per = get_avg_cer_of_method(predictions, benchmark) * 100\n",
        "  homograph = get_homograph_performance(predictions, benchmark) * 100\n",
        "\n",
        "  print(f\"PER: \\t\\t\\t{per:.4f}\")\n",
        "  print(f\"HOMOGRAPH: \\t\\t{homograph:.4f}\")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Inference"
      ],
      "metadata": {
        "id": "fTRgGM_8_Fwg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import time"
      ],
      "metadata": {
        "id": "owk5yIrGd5mE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "start_time = time.time()\n",
        "\n",
        "mapped_outputs = [text_to_phonemes(item[0]) for item in benchmark]\n",
        "\n",
        "total_time = time.time() - start_time\n",
        "avg_time = total_time / len(benchmark) if len(benchmark) > 0 else 0"
      ],
      "metadata": {
        "id": "8xzXN4KWOBWX"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Results"
      ],
      "metadata": {
        "id": "JAIAobLFCKCr"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "print_all_metrics(mapped_outputs)\n",
        "print(f\"TOTAL TIME:\\t\\t{total_time:.2f} (s)\")\n",
        "print(f\"AVG TIME:\\t\\t{avg_time:.4f} (s)+\")"
      ],
      "metadata": {
        "id": "E3OB9-tCWT7I",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "8e57d011-ed0b-4d4e-defe-1ed45e9ff56d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "PER: \t\t\t6.9152\n",
            "HOMOGRAPH: \t\t43.8679\n",
            "TOTAL TIME:\t\t6.82 (s)\n",
            "AVG TIME:\t\t0.0170 (s)+\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Runs\n",
        "\n",
        "## First:\n",
        "\n",
        "```\n",
        "PER: \t\t\t6.9152\n",
        "HOMOGRAPH: \t\t43.8679\n",
        "TOTAL TIME:\t\t6.58 (s)\n",
        "AVG TIME:\t\t0.0165 (s)+\n",
        "```\n",
        "\n",
        "## Second\n",
        "\n",
        "```\n",
        "PER: \t\t\t6.9152\n",
        "HOMOGRAPH: \t\t43.8679\n",
        "TOTAL TIME:\t\t6.67 (s)\n",
        "AVG TIME:\t\t0.0167 (s)+\n",
        "```\n",
        "\n",
        "## Third\n",
        "\n",
        "```\n",
        "PER: \t\t\t6.9152\n",
        "HOMOGRAPH: \t\t43.8679\n",
        "TOTAL TIME:\t\t6.65 (s)\n",
        "AVG TIME:\t\t0.0166 (s)+\n",
        "```\n",
        "\n",
        "## Fourth\n",
        "\n",
        "```\n",
        "PER: \t\t\t6.9152\n",
        "HOMOGRAPH: \t\t43.8679\n",
        "TOTAL TIME:\t\t7.16 (s)\n",
        "AVG TIME:\t\t0.0179 (s)+\n",
        "```\n",
        "\n",
        "## Fifth\n",
        "\n",
        "```\n",
        "PER: \t\t\t6.9152\n",
        "HOMOGRAPH: \t\t43.8679\n",
        "TOTAL TIME:\t\t6.82 (s)\n",
        "AVG TIME:\t\t0.0170 (s)+\n",
        "```"
      ],
      "metadata": {
        "id": "1ImhTHJY7bYr"
      }
    }
  ]
}