Upload translations_using_mbart_for_olympai_hackathon.ipynb

translations_using_mbart_for_olympai_hackathon.ipynb

@@ -0,0 +1,395 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Installing Libraries"
+      ],
+      "metadata": {
+        "id": "MHZGRsR57URH"
+      }
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "yR0_MKOOeRNO",
+        "outputId": "ba662b01-469b-44d1-e083-22c872672a18"
+      },
+      "source": [
+        "!pip install transformers -U -q"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.5/43.5 kB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.1/10.1 MB\u001b[0m \u001b[31m64.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m75.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25h"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "2RtEvp3Me4va",
+        "outputId": "288d9f19-a168-48b2-e1b9-f0402c04bce6"
+      },
+      "source": [
+        "! pip install sentencepiece"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (0.2.0)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "OLwUoKhxD-jt",
+        "outputId": "c44a998c-1fec-4cde-b072-5936390f468e"
+      },
+      "source": [
+        "!pip freeze | grep transformers"
+      ],
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "sentence-transformers==3.2.1\n",
+            "transformers==4.47.0\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## importing Libraries"
+      ],
+      "metadata": {
+        "id": "WnDCnz9x8MhT"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import gradio as gr\n",
+        "from PIL import Image\n",
+        "import pytesseract\n",
+        "from transformers import MBartForConditionalGeneration, MBart50Tokenizer\n"
+      ],
+      "metadata": {
+        "id": "FC_Wo01D8PxV"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from google.colab import drive\n",
+        "drive.mount('/content/drive')"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "kmCHgI4v6qxm",
+        "outputId": "682030b9-c6e4-4a83-e8f3-d88631e2c859"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Mounted at /content/drive\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Loading model"
+      ],
+      "metadata": {
+        "id": "DZ5W2COw7gju"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "from transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n",
+        "\n",
+        "tokenizer = AutoTokenizer.from_pretrained(\"facebook/mbart-large-50-many-to-many-mmt\")\n",
+        "model = AutoModelForSeq2SeqLM.from_pretrained(\"facebook/mbart-large-50-many-to-many-mmt\")"
+      ],
+      "metadata": {
+        "id": "aVursIUH6xHR"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## transating image functions"
+      ],
+      "metadata": {
+        "id": "mMeK4N6q8BWf"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def translate_image(img_path, src_lang, tgt_lang):\n",
+        "        # Extract text from the image using Tesseract OCR\n",
+        "        text = pytesseract.image_to_string(img_path)\n",
+        "        if not text.strip():\n",
+        "            return \"No text detected. Please upload a valid image.\", \"\"\n",
+        "\n",
+        "        # Translating the text\n",
+        "        tokenizer.src_lang = src_lang\n",
+        "        inputs = tokenizer(text, return_tensors=\"pt\")\n",
+        "        generated_tokens = model.generate(\n",
+        "            **inputs, forced_bos_token_id=tokenizer.lang_code_to_id[tgt_lang]\n",
+        "        )\n",
+        "        translated_text = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "HuH9KMzn8FnM"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Putting it all together in the gradio webpage"
+      ],
+      "metadata": {
+        "id": "OWhIkDbZ8YTb"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Installing necessary libraries\n",
+        "!pip install gradio pytesseract transformers sentencepiece\n",
+        "\n",
+        "# Installing Tesseract OCR\n",
+        "!apt-get install -y tesseract-ocr\n",
+        "!pip install Pillow\n",
+        "\n",
+        "# Importing libraries\n",
+        "import gradio as gr\n",
+        "from PIL import Image\n",
+        "import pytesseract\n",
+        "from transformers import MBartForConditionalGeneration, MBart50Tokenizer\n",
+        "\n",
+        "# Loading the MBart model and tokenizer\n",
+        "MODEL_NAME = \"facebook/mbart-large-50-many-to-many-mmt\"\n",
+        "tokenizer = MBart50Tokenizer.from_pretrained(MODEL_NAME)\n",
+        "model = MBartForConditionalGeneration.from_pretrained(MODEL_NAME)\n",
+        "\n",
+        "# Defining the OCR and translation function\n",
+        "def translate_image(img_path, src_lang, tgt_lang):\n",
+        "    try:\n",
+        "        # Extract text from the image using Tesseract OCR\n",
+        "        text = pytesseract.image_to_string(img_path)\n",
+        "        if not text.strip():\n",
+        "            return \"No text detected. Please upload a valid image.\", \"\"\n",
+        "\n",
+        "        # Translating the text\n",
+        "        tokenizer.src_lang = src_lang\n",
+        "        inputs = tokenizer(text, return_tensors=\"pt\")\n",
+        "        generated_tokens = model.generate(\n",
+        "            **inputs, forced_bos_token_id=tokenizer.lang_code_to_id[tgt_lang]\n",
+        "        )\n",
+        "        translated_text = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]\n",
+        "\n",
+        "        return text, translated_text\n",
+        "    except Exception as e:\n",
+        "        return f\"Error: {str(e)}\", \"\"\n",
+        "\n",
+        "# Defining the Gradio interface\n",
+        "with gr.Blocks() as app:\n",
+        "    gr.Markdown(\"## OCR and Translation App\")\n",
+        "    gr.Markdown(\"Upload an image, specify source and target languages, and get the translated text.\")\n",
+        "\n",
+        "    with gr.Row():\n",
+        "        img_input = gr.File(label=\"Upload Image\", type=\"filepath\")\n",
+        "        src_lang = gr.Textbox(label=\"Source Language Code (OCR works best with english)\")\n",
+        "        tgt_lang = gr.Textbox(label=\"Target Language Code (any target language)\")\n",
+        "\n",
+        "    with gr.Row():\n",
+        "        extracted_text = gr.Textbox(label=\"Extracted Text\")\n",
+        "        translated_text = gr.Textbox(label=\"Translated Text\")\n",
+        "\n",
+        "    translate_button = gr.Button(\"Translate\")\n",
+        "    translate_button.click(\n",
+        "        translate_image, inputs=[img_input, src_lang, tgt_lang], outputs=[extracted_text, translated_text]\n",
+        "    )\n",
+        "\n",
+        "# Launching the app\n",
+        "app.launch()\n",
+        "\n",
+        "# Language codes. Note - The OCR app can only translate from english to the languges mentioned below\n",
+        "\n",
+        "# Arabic (ar_AR), Czech (cs_CZ), German (de_DE), English (en_XX), Spanish (es_XX),\n",
+        "# Estonian (et_EE), Finnish (fi_FI), French (fr_XX), Gujarati (gu_IN), Hindi (hi_IN),\n",
+        "# Italian (it_IT), Japanese (ja_XX), Kazakh (kk_KZ), Korean (ko_KR), Lithuanian (lt_LT),\n",
+        "# Latvian (lv_LV), Burmese (my_MM), Nepali (ne_NP), Dutch (nl_XX), Romanian (ro_RO),\n",
+        "# Russian (ru_RU), Sinhala (si_LK), Turkish (tr_TR), Vietnamese (vi_VN), Chinese (zh_CN),\n",
+        "# Afrikaans (af_ZA), Azerbaijani (az_AZ), Bengali (bn_IN), Persian (fa_IR), Hebrew (he_IL),\n",
+        "# Croatian (hr_HR), Indonesian (id_ID), Georgian (ka_GE),\n",
+        "# Khmer (km_KH), Macedonian (mk_MK), Malayalam (ml_IN), Mongolian (mn_MN), Marathi (mr_IN),\n",
+        "# Polish (pl_PL), Pashto (ps_AF), Portuguese ), Swedish (sv_SE), Swahili (sw_KE), Tamil (ta_IN),\n",
+        "# Telugu (te_IN), Thai (th_TH), Tagalog (tl_XX), Ukrainian (uk_UA), Urdu (ur_PK), Xhosa (xh_ZA),\n",
+        "# Galician (gl_ES), Slovene (sl_SI)\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000
+        },
+        "id": "LPq0MtL0Kmvz",
+        "outputId": "c06f9b31-0f1b-4da6-8150-d97b259312cc"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Requirement already satisfied: gradio in /usr/local/lib/python3.10/dist-packages (5.8.0)\n",
+            "Requirement already satisfied: pytesseract in /usr/local/lib/python3.10/dist-packages (0.3.13)\n",
+            "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.46.3)\n",
+            "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (0.2.0)\n",
+            "Requirement already satisfied: aiofiles<24.0,>=22.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (23.2.1)\n",
+            "Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.7.1)\n",
+            "Requirement already satisfied: fastapi<1.0,>=0.115.2 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.115.6)\n",
+            "Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio) (0.4.0)\n",
+            "Requirement already satisfied: gradio-client==1.5.1 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.5.1)\n",
+            "Requirement already satisfied: httpx>=0.24.1 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.28.0)\n",
+            "Requirement already satisfied: huggingface-hub>=0.25.1 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.26.3)\n",
+            "Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.1.4)\n",
+            "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.1.5)\n",
+            "Requirement already satisfied: numpy<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.26.4)\n",
+            "Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.10.12)\n",
+            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio) (24.2)\n",
+            "Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.2.2)\n",
+            "Requirement already satisfied: pillow<12.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (11.0.0)\n",
+            "Requirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.10.3)\n",
+            "Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio) (0.25.1)\n",
+            "Requirement already satisfied: python-multipart>=0.0.18 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.0.19)\n",
+            "Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.0.2)\n",
+            "Requirement already satisfied: ruff>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.8.2)\n",
+            "Requirement already satisfied: safehttpx<0.2.0,>=0.1.6 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.1.6)\n",
+            "Requirement already satisfied: semantic-version~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.10.0)\n",
+            "Requirement already satisfied: starlette<1.0,>=0.40.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.41.3)\n",
+            "Requirement already satisfied: tomlkit<0.14.0,>=0.12.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.13.2)\n",
+            "Requirement already satisfied: typer<1.0,>=0.12 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.15.0)\n",
+            "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.12.2)\n",
+            "Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.32.1)\n",
+            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==1.5.1->gradio) (2024.10.0)\n",
+            "Requirement already satisfied: websockets<15.0,>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio-client==1.5.1->gradio) (14.1)\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.16.1)\n",
+            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2024.9.11)\n",
+            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.32.3)\n",
+            "Requirement already satisfied: tokenizers<0.21,>=0.20 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.20.3)\n",
+            "Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.5)\n",
+            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.6)\n",
+            "Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<5.0,>=3.0->gradio) (3.10)\n",
+            "Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<5.0,>=3.0->gradio) (1.3.1)\n",
+            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5.0,>=3.0->gradio) (1.2.2)\n",
+            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (2024.8.30)\n",
+            "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (1.0.7)\n",
+            "Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx>=0.24.1->gradio) (0.14.0)\n",
+            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2.8.2)\n",
+            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
+            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
+            "Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (0.7.0)\n",
+            "Requirement already satisfied: pydantic-core==2.27.1 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (2.27.1)\n",
+            "Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (8.1.7)\n",
+            "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
+            "Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (13.9.4)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.4.0)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.2.3)\n",
+            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas<3.0,>=1.0->gradio) (1.16.0)\n",
+            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
+            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.18.0)\n",
+            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
+            "Reading package lists... Done\n",
+            "Building dependency tree... Done\n",
+            "Reading state information... Done\n",
+            "tesseract-ocr is already the newest version (4.1.1-2.1build1).\n",
+            "0 upgraded, 0 newly installed, 0 to remove and 49 not upgraded.\n",
+            "Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (11.0.0)\n",
+            "Running Gradio in a Colab notebook requires sharing enabled. Automatically setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
+            "\n",
+            "Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
+            "* Running on public URL: https://08e78290e64bdebf00.gradio.live\n",
+            "\n",
+            "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<IPython.core.display.HTML object>"
+            ],
+            "text/html": [
+              "<div><iframe src=\"https://08e78290e64bdebf00.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": []
+          },
+          "metadata": {},
+          "execution_count": 17
+        }
+      ]
+    }
+  ]
+}