{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "WEY5MiKLzurH" }, "source": [ "# Setup Environment" ] }, { "cell_type": "code", "source": [ "! pip install hazm==0.10.0" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "QtQ-huXYtepn", "outputId": "7755d71f-82c4-4a8f-dd14-919767ccd82a" }, "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[31m1.9 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[31m19.1 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[31m72.3 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[31m77.3 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[31m18.7 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[31m37.9 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[31m16.0 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[31m15.7 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=ced3adb209606d785c23d09dcadd043fd23f7c63a88a04dc1a3922017818b447\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": "954f89a9223948ee9ece2a3af9016355" } }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "! pip install persian_phonemizer" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "JJ9VISNqZS6m", "outputId": "56e5c328-ecda-429f-e8b7-d9044dae080a" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting persian_phonemizer\n", " Downloading persian_phonemizer-0.4.0-py3-none-any.whl.metadata (3.1 kB)\n", "Requirement already satisfied: spacy>=3.3 in /usr/local/lib/python3.11/dist-packages (from persian_phonemizer) (3.8.5)\n", "Collecting g2p-fa (from persian_phonemizer)\n", " Downloading g2p_fa-1.1.0-py3-none-any.whl.metadata (2.7 kB)\n", "Requirement already satisfied: hazm in /usr/local/lib/python3.11/dist-packages (from persian_phonemizer) (0.10.0)\n", "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (3.0.12)\n", "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (1.0.5)\n", "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (1.0.12)\n", "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (2.0.11)\n", "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (3.0.9)\n", "Requirement already satisfied: thinc<8.4.0,>=8.3.4 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (8.3.6)\n", "Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (1.1.3)\n", "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (2.5.1)\n", "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (2.0.10)\n", "Requirement already satisfied: weasel<0.5.0,>=0.1.0 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (0.4.1)\n", "Requirement already satisfied: typer<1.0.0,>=0.3.0 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (0.15.3)\n", "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (4.67.1)\n", "Requirement already satisfied: numpy>=1.19.0 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (1.24.3)\n", "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (2.32.3)\n", "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (2.11.4)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (3.1.6)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (75.2.0)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (24.2)\n", "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /usr/local/lib/python3.11/dist-packages (from spacy>=3.3->persian_phonemizer) (3.5.0)\n", "Requirement already satisfied: torch in /usr/local/lib/python3.11/dist-packages (from g2p-fa->persian_phonemizer) (2.6.0+cu124)\n", "Requirement already satisfied: fasttext-wheel<0.10.0,>=0.9.2 in /usr/local/lib/python3.11/dist-packages (from hazm->persian_phonemizer) (0.9.2)\n", "Requirement already satisfied: flashtext<3.0,>=2.7 in /usr/local/lib/python3.11/dist-packages (from hazm->persian_phonemizer) (2.7)\n", "Requirement already satisfied: gensim<5.0.0,>=4.3.1 in /usr/local/lib/python3.11/dist-packages (from hazm->persian_phonemizer) (4.3.3)\n", "Requirement already satisfied: nltk<4.0.0,>=3.8.1 in /usr/local/lib/python3.11/dist-packages (from hazm->persian_phonemizer) (3.9.1)\n", "Requirement already satisfied: python-crfsuite<0.10.0,>=0.9.9 in /usr/local/lib/python3.11/dist-packages (from hazm->persian_phonemizer) (0.9.11)\n", "Requirement already satisfied: scikit-learn<2.0.0,>=1.2.2 in /usr/local/lib/python3.11/dist-packages (from hazm->persian_phonemizer) (1.6.1)\n", "Requirement already satisfied: pybind11>=2.2 in /usr/local/lib/python3.11/dist-packages (from fasttext-wheel<0.10.0,>=0.9.2->hazm->persian_phonemizer) (2.13.6)\n", "Requirement already satisfied: scipy<1.14.0,>=1.7.0 in /usr/local/lib/python3.11/dist-packages (from gensim<5.0.0,>=4.3.1->hazm->persian_phonemizer) (1.13.1)\n", "Requirement already satisfied: smart-open>=1.8.1 in /usr/local/lib/python3.11/dist-packages (from gensim<5.0.0,>=4.3.1->hazm->persian_phonemizer) (7.1.0)\n", "Requirement already satisfied: language-data>=1.2 in /usr/local/lib/python3.11/dist-packages (from langcodes<4.0.0,>=3.2.0->spacy>=3.3->persian_phonemizer) (1.3.0)\n", "Requirement already satisfied: click in /usr/local/lib/python3.11/dist-packages (from nltk<4.0.0,>=3.8.1->hazm->persian_phonemizer) (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->persian_phonemizer) (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->persian_phonemizer) (2024.11.6)\n", "Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy>=3.3->persian_phonemizer) (0.7.0)\n", "Requirement already satisfied: pydantic-core==2.33.2 in /usr/local/lib/python3.11/dist-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy>=3.3->persian_phonemizer) (2.33.2)\n", "Requirement already satisfied: typing-extensions>=4.12.2 in /usr/local/lib/python3.11/dist-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy>=3.3->persian_phonemizer) (4.13.2)\n", "Requirement already satisfied: typing-inspection>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4->spacy>=3.3->persian_phonemizer) (0.4.0)\n", "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests<3.0.0,>=2.13.0->spacy>=3.3->persian_phonemizer) (3.4.1)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests<3.0.0,>=2.13.0->spacy>=3.3->persian_phonemizer) (3.10)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests<3.0.0,>=2.13.0->spacy>=3.3->persian_phonemizer) (2.4.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests<3.0.0,>=2.13.0->spacy>=3.3->persian_phonemizer) (2025.4.26)\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->persian_phonemizer) (3.6.0)\n", "Requirement already satisfied: blis<1.4.0,>=1.3.0 in /usr/local/lib/python3.11/dist-packages (from thinc<8.4.0,>=8.3.4->spacy>=3.3->persian_phonemizer) (1.3.0)\n", "Requirement already satisfied: confection<1.0.0,>=0.0.1 in /usr/local/lib/python3.11/dist-packages (from thinc<8.4.0,>=8.3.4->spacy>=3.3->persian_phonemizer) (0.1.5)\n", "INFO: pip is looking at multiple versions of thinc to determine which version is compatible with other requirements. This could take a while.\n", "Collecting thinc<8.4.0,>=8.3.4 (from spacy>=3.3->persian_phonemizer)\n", " Downloading thinc-8.3.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (15 kB)\n", "Collecting blis<1.3.0,>=1.2.0 (from thinc<8.4.0,>=8.3.4->spacy>=3.3->persian_phonemizer)\n", " Downloading blis-1.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.4 kB)\n", "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0.0,>=0.3.0->spacy>=3.3->persian_phonemizer) (1.5.4)\n", "Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0.0,>=0.3.0->spacy>=3.3->persian_phonemizer) (13.9.4)\n", "Requirement already satisfied: cloudpathlib<1.0.0,>=0.7.0 in /usr/local/lib/python3.11/dist-packages (from weasel<0.5.0,>=0.1.0->spacy>=3.3->persian_phonemizer) (0.21.0)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->spacy>=3.3->persian_phonemizer) (3.0.2)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch->g2p-fa->persian_phonemizer) (3.18.0)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch->g2p-fa->persian_phonemizer) (3.4.2)\n", "Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch->g2p-fa->persian_phonemizer) (2025.3.2)\n", "Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch->g2p-fa->persian_phonemizer)\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->g2p-fa->persian_phonemizer)\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->g2p-fa->persian_phonemizer)\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->g2p-fa->persian_phonemizer)\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->g2p-fa->persian_phonemizer)\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->g2p-fa->persian_phonemizer)\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->g2p-fa->persian_phonemizer)\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->g2p-fa->persian_phonemizer)\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->g2p-fa->persian_phonemizer)\n", " Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n", "Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch->g2p-fa->persian_phonemizer) (0.6.2)\n", "Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch->g2p-fa->persian_phonemizer) (2.21.5)\n", "Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->g2p-fa->persian_phonemizer) (12.4.127)\n", "Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch->g2p-fa->persian_phonemizer)\n", " Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n", "Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch->g2p-fa->persian_phonemizer) (3.2.0)\n", "Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch->g2p-fa->persian_phonemizer) (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->g2p-fa->persian_phonemizer) (1.3.0)\n", "Requirement already satisfied: marisa-trie>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from language-data>=1.2->langcodes<4.0.0,>=3.2.0->spacy>=3.3->persian_phonemizer) (1.2.1)\n", "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy>=3.3->persian_phonemizer) (3.0.0)\n", "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy>=3.3->persian_phonemizer) (2.19.1)\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->persian_phonemizer) (1.17.2)\n", "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0.0,>=0.3.0->spacy>=3.3->persian_phonemizer) (0.1.2)\n", "Downloading persian_phonemizer-0.4.0-py3-none-any.whl (7.2 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.2/7.2 MB\u001b[0m \u001b[31m62.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading g2p_fa-1.1.0-py3-none-any.whl (6.2 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.2/6.2 MB\u001b[0m \u001b[31m104.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading thinc-8.3.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.9 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.9/3.9 MB\u001b[0m \u001b[31m98.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading 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[31m4.2 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[31m104.5 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[31m80.6 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[31m50.3 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[31m2.3 MB/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[31m5.8 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[31m12.0 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[31m7.1 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[31m6.4 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[31m90.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading blis-1.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.7 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.7/11.7 MB\u001b[0m \u001b[31m112.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, blis, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, thinc, g2p-fa, persian_phonemizer\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: blis\n", " Found existing installation: blis 1.3.0\n", " Uninstalling blis-1.3.0:\n", " Successfully uninstalled blis-1.3.0\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: thinc\n", " Found existing installation: thinc 8.3.6\n", " Uninstalling thinc-8.3.6:\n", " Successfully uninstalled thinc-8.3.6\n", "Successfully installed blis-1.2.1 g2p-fa-1.1.0 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 persian_phonemizer-0.4.0 thinc-8.3.4\n" ] } ] }, { "cell_type": "code", "source": [ "! pip install jiwer" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "5OD5ZtfTck77", "outputId": "775bc630-e1d3-49d1-9e0f-62f96dc65ee5" }, "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[31m35.8 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 os\n", "import re\n", "from tqdm import tqdm\n", "import csv\n", "import pandas as pd\n", "import json\n", "import itertools\n", "from jiwer import cer" ], "metadata": { "id": "DLEJ-KSecpyV" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "from persian_phonemizer import Phonemizer\n", "phonemizer = Phonemizer()\n", "phonemizer.phonemize('دلم میخواست برم ')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 35 }, "id": "my5HlSvaaz6h", "outputId": "6f4c048f-412b-4940-97a7-6a6eb284881a" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "'dele mæʒ miːxævɒːstʰ bæɾm'" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" } }, "metadata": {}, "execution_count": 4 } ] }, { "cell_type": "markdown", "source": [ "# mapping" ], "metadata": { "id": "VtxEYym69RUH" } }, { "cell_type": "code", "source": [ "output_to_phonetics_map = {\n", " 'м': 'm',\n", " 'ʷ':' v',\n", " 'c': 'k',\n", " 'ĉ': 'C',\n", " 'č': 'C',\n", " '̕': \"?\",\n", " \"'\": '?',\n", " 'ʔ': \"?\",\n", " 'ꞌ': \"?\",\n", " '̛': \"?\",\n", " '’': \"?\",\n", " 'ʼ': \"?\",\n", " \"'\": '?',\n", " 'â': 'A',\n", " 'â': 'A',\n", " 'ȃ': 'A',\n", " 'ž': 'Z',\n", " 'š': 'S',\n", " 'W': 'v',\n", " 'β': 'f',\n", " 'е': 'e',\n", " '`': \"?\",\n", " 'ɑ': 'A',\n", " 'ɑ': 'A',\n", " 'ʃ': 'S',\n", " 'ð': 'z',\n", " 'ɾ': 'r',\n", " 'æ': 'a',\n", " 'ɪ': 'e',\n", " 'χ': 'x',\n", " 'ɣ': 'q',\n", " 'ʒ': 'Z',\n", " ':': '',\n", " 'ː': '',\n", " 'ā': 'A',\n", " 'ː': '',\n", " 'ä': 'A',\n", " 'á': 'A',\n", " 'š': 'S',\n", " 'ū': 'u',\n", " 'û': 'u',\n", " 'ś': 's',\n", " 'ī': 'i',\n", " 'í': 'i',\n", " 'î': 'i',\n", " 'é': 'e',\n", " 'ḥ': 'h',\n", " 'ɒ': 'A',\n", " 'ʰ': '',\n", " 'ə': 'e',\n", " 'R': 'r',\n", " 'W': 'v',\n", " 'Q': 'q',\n", " 'T': 't',\n", " 'Y': 'y',\n", " 'P': 'p',\n", " 'D': 'd',\n", " 'F': 'f',\n", " 'H': 'h',\n", " 'J': 'j',\n", " 'L': 'l',\n", " 'X': 'x',\n", " 'V': 'v',\n", " 'B': 'b',\n", " 'N': 'n',\n", " 'M': 'm',\n", " 'K': 'k',\n", " 'G': 'g',\n", " 'U': 'u',\n", " 'O': 'o',\n", " 'I': 'i',\n", " 'E': 'e',\n", " 'ŋ': 'ng',\n", " '.': '',\n", " 'ɛ': 'e',\n", " 'ʊ': 'u',\n", " \"ˈ\": '?',\n", " 'ù': 'u',\n", " 'θ': 's',\n", " '̪': '',\n", " 'ũ': 'u',\n", " '_': '',\n", " 'ç': 'C',\n", " 'ĝ': 'q',\n", " 'ɢ': 'q',\n", " 'ː': '',\n", " 'í': 'i',\n", " 'ŝ': 'S',\n", " '!': '',\n", " 'ǧ': 'q',\n", " 'ʻ': '?',\n", " 'è': 'e',\n", " '�': '',\n", " 'ú': 'u',\n", " 'ô': 'o',\n", " 'ē': 'e',\n", " 'à': 'A',\n", " 'ă': 'A',\n", " 'ǐ': 'i',\n", " 'ü': 'u',\n", " '\\u200e': '',\n", " 'ğ': 'q',\n", " 'ṣ': 'S',\n", " 'â': 'A',\n", " 'â': 'A',\n", " 'ȃ': 'A',\n", " 'ž': 'Z',\n", " 'š': 'S',\n", " 'ā': 'A',\n", " 'ː': '',\n", " 'ä': 'A',\n", " 'á': 'A',\n", " 'š': 'S',\n", " 'ū': 'u',\n", " 'û': 'u',\n", " 'ś': 'S',\n", " 'ī': 'i',\n", " 'í': 'i',\n", " 'î': 'i',\n", " 'é': 'e',\n", "}\n", "\n", "consonants_regex = '(?=' + '|'.join(['q', 'r', 't', 'y', 'p', 's', 'd', 'f', 'g', 'h', 'j', 'k', 'l', 'z', 'x', 'c', 'v', 'b', 'n', 'm', 'Q', 'R', 'T', 'Y', 'P', 'S', 'D', 'F', 'G', 'H', 'J', 'K', 'L', 'Z', 'X', 'C', 'V', 'B', 'N', 'M' ]) + ')'\n", "vowels_regex = '(?=' + '|'.join(['a', 'A', 'e', 'i', 'u', 'o']) + ')'\n", "\n", "\n", "def replace_phonetic_characters(input_string, char_map=output_to_phonetics_map, from_phonetics=False):\n", " substituted = re.sub(r'tʃʰ', 'C', input_string)\n", " substituted = re.sub(r't͡ʃ', 'C', input_string)\n", " substituted = re.sub(r'tʃ', 'C', substituted)\n", " substituted = re.sub(r't͡S', 'C', substituted)\n", " substituted = re.sub(r'ow', 'o', substituted)\n", " substituted = re.sub('d͡ʒ', 'j', substituted)\n", " substituted = re.sub('dʒ', 'j', substituted)\n", "\n", " # Create a translation table using str.maketrans\n", " translation_table = str.maketrans(char_map)\n", "\n", " # Use str.translate to replace characters based on the translation table\n", " translated = substituted.translate(translation_table)\n", "\n", " return translated" ], "metadata": { "id": "TKx8oA1n7rKh" }, "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": "63d62243-fa2f-4241-bc6c-a9d5b24f8980" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "--2025-05-10 10:07:38-- https://huggingface.co/datasets/MahtaFetrat/SentenceBench/raw/main/SentenceBench.csv\n", "Resolving huggingface.co (huggingface.co)... 18.160.143.76, 18.160.143.99, 18.160.143.75, ...\n", "Connecting to huggingface.co (huggingface.co)|18.160.143.76|: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 0.01s \n", "\n", "2025-05-10 10:07:38 (4.42 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": "584e795c-1801-4594-be3f-e4426a16925f" }, "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", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
datasetgraphemephonemehomograph wordpronunciation
0homographمن قدر تو را می‌دانمman qadr-e to rA mi-dAnamقدرqadr
1homographاز قضای الهی به قدر الهی پناه می‌برم?az qazAy ?elAhi be qadar-e ?elAhi panAh mi-baramقدرqadar
2homographبه دست و صورتم کرم زدمbe dast-o suratam kerem zadamکرمkerem
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "
\n", "
\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": "57eed88d-7ae2-4c1d-fd40-4f8f09e8dd03" }, "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": "60f4e58c-8529-4d62-88ca-795413c40385" }, "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": "19aeaf85-6001-4d7f-e46f-e65b05b0a861" }, "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": "CLKaERek4u_D" }, "source": [ "## PER Evaluation" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "nBee9xG54u_E" }, "outputs": [], "source": [ "def remove_non_word_chars(text):\n", " pattern = r'[^\\w\\s\\?]'\n", " cleaned_text = re.sub(pattern, ' ', text)\n", " return cleaned_text" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "W8PoNV9V4u_E" }, "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": "YD0cvnn74u_E" }, "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": "6OQQDual4u_E" }, "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": "ncWQnPdW4u_E" }, "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", "source": [ "## Homograph Evaluation" ], "metadata": { "id": "oBgNtpFQDwku" } }, { "cell_type": "code", "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" ], "metadata": { "id": "J445ULEvEEDn" }, "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "source": [ "# Full bench" ], "metadata": { "id": "JGEUIrbi9kNH" } }, { "cell_type": "code", "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]" ], "metadata": { "id": "fGzQvL8V9mln" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "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}\")" ], "metadata": { "id": "DpSqE5oPbmAy" }, "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "source": [ "# Sentence Inference" ], "metadata": { "id": "_-mKfiwYIMdQ" } }, { "cell_type": "code", "source": [ "from hazm import WordTokenizer, Normalizer\n", "tokenizer = WordTokenizer()\n", "normalizer = Normalizer()" ], "metadata": { "id": "PNuCMdIuVPf5" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "def sentence_inference(sent):\n", " phonemes = []\n", " tokens = tokenizer.tokenize(normalizer.normalize(sent))\n", " i = 0\n", " while i < len(tokens):\n", " subsent = ' '.join(tokens[i:i+3])\n", " try:\n", " subphoneme = phonemizer.phonemize(subsent)\n", " except:\n", " subphoneme = ''\n", " phonemes.append(subphoneme)\n", " i += len(tokens[i:i+3])\n", "\n", " phoneme = ' '.join(phonemes)\n", " return phoneme" ], "metadata": { "id": "rTPVMXEGU_9r" }, "execution_count": null, "outputs": [] }, { "cell_type": "markdown", "source": [ "# outputs" ], "metadata": { "id": "fRaAhTMsMHBJ" } }, { "cell_type": "code", "source": [ "import time\n", "from tqdm import tqdm\n", "\n", "# Initialize variables\n", "outputs = []\n", "start_time = time.time() # Start total timer\n", "\n", "# Process each sample with progress bar\n", "for g, p, _, _ in tqdm(benchmark, desc=\"Running inference\"):\n", " o = sentence_inference(g)\n", " outputs.append(o)\n", "\n", "# Calculate timing stats\n", "total_time = time.time() - start_time\n", "avg_time = total_time / len(benchmark) if benchmark else 0" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "acc51819-0c98-4eda-a4cc-270f9707e370", "id": "PYn9z4GiMHBf" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "Running inference: 100%|██████████| 400/400 [01:15<00:00, 5.33it/s]\n" ] } ] }, { "cell_type": "code", "source": [ "mapped_outputs = []\n", "for o in outputs:\n", " mapped = replace_phonetic_characters(o)\n", " mapped_outputs.append(mapped)" ], "metadata": { "id": "90gAxDT-GMhI" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "print_all_metrics(mapped_outputs)\n", "print(f\"TOTAL TIME:\\t\\t{total_time:.4f} (s)\")\n", "print(f\"AVG TIME:\\t\\t{avg_time:.4f} (s)\")" ], "metadata": { "id": "zP4Tcj285Ij0", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "5986173e-4d6b-4ff6-b18c-b1e72e3afd83" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "PER: \t\t\t25.2989\n", "HOMOGRAPH: \t\t29.2453\n", "TOTAL TIME:\t\t75.0611 (s)\n", "AVG TIME:\t\t0.1877 (s)\n" ] } ] }, { "cell_type": "markdown", "source": [ "# Runs\n", "\n", "## First:\n", "\n", "```\n", "PER: \t\t\t25.2111\n", "HOMOGRAPH: \t\t29.7170\n", "TOTAL TIME:\t\t85.6780 (s)\n", "AVG TIME:\t\t0.2142 (s)\n", "```\n", "\n", "## Second\n", "\n", "```\n", "PER: \t\t\t25.1991\n", "HOMOGRAPH: \t\t29.7170\n", "TOTAL TIME:\t\t41.5983 (s)\n", "AVG TIME:\t\t0.1040 (s)\n", "```\n", "\n", "## Third\n", "\n", "```\n", "PER: \t\t\t25.2278\n", "HOMOGRAPH: \t\t28.7736\n", "TOTAL TIME:\t\t78.4948 (s)\n", "AVG TIME:\t\t0.1962 (s)\n", "```\n", "\n", "\n", "## Fourth\n", "\n", "```\n", "PER: \t\t\t25.4065\n", "HOMOGRAPH: \t\t28.7736\n", "TOTAL TIME:\t\t79.8478 (s)\n", "AVG TIME:\t\t0.1996 (s)\n", "```\n", "\n", "## Fifth\n", "\n", "```\n", "PER: \t\t\t25.2989\n", "HOMOGRAPH: \t\t29.2453\n", "TOTAL TIME:\t\t75.0611 (s)\n", "AVG TIME:\t\t0.1877 (s)\n", "```" ], "metadata": { "id": "5YPY-B2DjHW7" } } ] }