Upload 9 files

Text2List.ipynb

@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "94c5b577-d632-422a-a82f-f357f36d491b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def text_to_list():\n",
+    "    text_list = [      \n",
+    "    # Hindi script for English numbers (11-19)\n",
+    "    'इलेवन', 'ट्वेल्व', 'थर्टीन', 'फोर्टीन', 'फिफ्टीन', 'सिक्स्टीन', 'सेवन्टीन', 'एटीन', 'नाइन्टीन',    \n",
+    "    # Hindi numbers (11-19)\n",
+    "    'ग्यारह', 'बारह', 'तेरह','तेरा ', 'चौदह', 'पंद्रह', 'सोलह','सोल्ला' 'सत्रह', 'सतरा', 'अठारा', 'उनाइस','अठारह', 'उन्नीस',\n",
+    "    # Hindi script for English multiples of ten (20, 30, ..., 90)\n",
+    "    'ट्वेंटी', 'थर्टी', 'फोर्टी', 'फिफ्टी', 'सिक्स्टी', 'सेवेन्टी', 'सेवंटी', 'सत्तर','सेवनटी','सेवेनटी','सेवांटी','एटी', 'नाइंटी',   \n",
+    "    # Hindi multiples of ten (20, 30, ..., 90)\n",
+    "    'बीस', 'तीस', 'चालीस', 'पचास', 'साठ', 'सत्तर', 'अस्सी', 'नब्बे',\n",
+    "    # Hindi script for English combinations of 21-29\n",
+    "    'ट्वेंटी वन', 'ट्वेंटी टू', 'ट्वेंटी थ्री', 'ट्वेंटी फोर', 'ट्वेंटी फाइव', 'ट्वेंटी सिक्स', 'ट्वेंटी सेवन', 'ट्वेंटी एट', 'ट्वेंटी नाइन',    \n",
+    "    # Hindi combinations of 21-29\n",
+    "    'इक्कीस', 'बाईस', 'तेईस', 'चौबीस', 'पच्चीस', 'छब्बीस', 'सत्ताईस', 'अट्ठाईस', 'उनतीस',\n",
+    "    # Hindi script for English combinations of 31-39\n",
+    "    'थर्टी वन', 'थर्टी टू', 'थर्टी थ्री', 'थर्टी फोर', 'थर्टी फाइव', 'थर्टी सिक्स', 'थर्टी सेवन', 'थर्टी एट', 'थर्टी नाइन',    \n",
+    "    # Hindi combinations of 31-39\n",
+    "    'इकतीस', 'बत्तीस', 'तेतीस', 'चौंतीस', 'पैंतीस', 'छत्तीस', 'सैंतीस', 'अड़तीस', 'उनतालीस',\n",
+    "    # Hindi script for English combinations of 41-49\n",
+    "    'फोर्टी वन', 'फोर्टी टू', 'फोर्टी थ्री', 'फोर्टी फोर', 'फोर्टी फाइव', 'फोर्टी सिक्स', 'फोर्टी सेवन', 'फोर्टी एट', 'फोर्टी नाइन',    \n",
+    "    # Hindi combinations of 41-49\n",
+    "    'इकतालीस', 'बयालीस', 'तैंतालीस', 'चौंतालीस', 'पैंतालीस', 'छयालिस', 'सैंतालीस', 'अड़तालीस', 'उनचास',\n",
+    "    # Hindi script for English combinations of 51-59\n",
+    "    'फिफ्टी वन', 'फिफ्टी टू', 'फिफ्टी थ्री', 'फिफ्टी फोर', 'फिफ्टी फाइव', 'फिफ्टी सिक्स', 'फिफ्टी सेवन', 'फिफ्टी एट', 'फिफ्टी नाइन',    \n",
+    "    # Hindi combinations of 51-59\n",
+    "    'इक्यावन', 'बावन', 'तिरेपन', 'चौवन', 'पचपन', 'छप्पन', 'सत्तावन','संतावन', 'अट्ठावन', 'उनसठ','अंठावन','उंसट',\n",
+    "    # Hindi script for English combinations of 61-69\n",
+    "    'सिक्स्टी वन', 'सिक्स्टी टू', 'सिक्स्टी थ्री', 'सिक्स्टी फोर', 'सिक्स्टी फाइव', 'सिक्स्टी सिक्स', 'सिक्स्टी सेवन', 'सिक्स्टी एट', 'सिक्स्टी नाइन',    \n",
+    "    # Hindi combinations of 61-69\n",
+    "    'इकसठ', 'बासठ', 'तिरसठ', 'चौंसठ', 'पैंसठ', 'छियासठ', 'सड़सठ', 'अड़सठ', 'उनहत्तर',\n",
+    "    # Hindi script for English combinations of 71-79\n",
+    "    'सेवेन्टी वन', 'सेवेन्टी टू', 'सेवेन्टी थ्री', 'सेवेन्टी फोर', 'सेवेन्टी फाइव', 'सेवेन्टी सिक्स', 'सेवेन्टी सेवन', 'सेवेन्टी एट', 'सेवेन्टी नाइन',    \n",
+    "    # Hindi combinations of 71-79\n",
+    "    'इकहत्तर', 'बहत्तर', 'तिहत्तर', 'तियत्तर','तीहत्तर','पचत्तर', 'चिहत्तर', 'अटत्तर', 'उनासी'  'चौहत्तर', 'पचहत्तर', 'छिहत्तर', 'सतहत्तर', 'अठहत्तर', 'उन्यासी','उनासी','अठत्तर',\n",
+    "    # Hindi script for English combinations of 81-89\n",
+    "    'एटी वन', 'एटी टू', 'एटी थ्री', 'एटी फोर', 'एटी फाइव', 'एटी सिक्स', 'एटी सेवन', 'एटी एट', 'एटी नाइन',    \n",
+    "    # Hindi combinations of 81-89\n",
+    "    'इक्यासी', 'बयासी', 'तिरासी', 'चौरासी', 'पचासी', 'छियासी', 'सतासी', 'अठासी', 'नवासी',\n",
+    "    # Hindi script for English combinations of 91-99\n",
+    "    'नाइंटी वन', 'नाइंटी टू', 'नाइंटी थ्री', 'नाइंटी फोर', 'नाइंटी फाइव', 'नाइंटी सिक्स', 'नाइंटी सेवन', 'नाइंटी एट', 'नाइंटी नाइन',   \n",
+    "    # Hindi combinations of 91-99\n",
+    "    'इक्यानवे', 'बानवे', 'तिरानवे', 'चौरानवे', 'पचानवे', 'छियानवे', 'सतानवे', 'अठानवे', 'निन्यानवे',\n",
+    "    # Hindi script for English numbers (0-10)\n",
+    "    'ज़ीरो', 'वन', 'टू', 'थ्री', 'फोर', 'फाइव', 'सिक्स', 'सेवन', 'एट', 'नाइन', 'टेन', \n",
+    "    # Hindi numbers (0-10)\n",
+    "    'जीरो', 'एक', 'दो', 'तीन', 'चार', 'पांच', 'छह', 'सात', 'आठ', 'नौ', 'दस', \n",
+    "    # Hindi script for 100\n",
+    "    'हंड्रेड',\n",
+    "    # Hindi for 100\n",
+    "    'सौ',\n",
+    "]\n",
+    "\n",
+    "    return text_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "787fa243-0dba-4a35-b479-2e9198dc6af1",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

convert2list.ipynb

@@ -0,0 +1,151 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "b52e9a66-a8e9-4f56-91fd-8564b5b636fc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "जीरो एक दो तीन चार पांच छह सात आठ नौ दस जीरो एक दो तीन चार पांच\n"
+     ]
+    }
+   ],
+   "source": [
+    "# import nbimporter\n",
+    "import nbimporter\n",
+    "from Text2List import text_to_list\n",
+    "def convert_to_list(text, text_list):\n",
+    "    matched_words = []\n",
+    "    unmatched_text = ''  # To accumulate unmatched characters\n",
+    "\n",
+    "    # Sort text_list by length in descending order to prioritize longest matches first\n",
+    "    text_list_sorted = sorted(text_list, key=len, reverse=True)\n",
+    "\n",
+    "    while text:\n",
+    "        matched = False\n",
+    "        for word in text_list_sorted:\n",
+    "            if text.startswith(word):\n",
+    "                # Add any accumulated unmatched text before appending the matched word\n",
+    "                if unmatched_text:\n",
+    "                    matched_words.append(unmatched_text)\n",
+    "                    unmatched_text = ''  # Reset unmatched text accumulator\n",
+    "\n",
+    "                matched_words.append(word)\n",
+    "                text = text[len(word):]  # Remove the matched part from text\n",
+    "                matched = True\n",
+    "                break\n",
+    "\n",
+    "        if not matched:\n",
+    "            # Accumulate unmatched characters\n",
+    "            unmatched_text += text[0]\n",
+    "            text = text[1:]\n",
+    "\n",
+    "    # If there's any remaining unmatched text, add it to the result\n",
+    "    if unmatched_text:\n",
+    "        matched_words.append(unmatched_text)\n",
+    "\n",
+    "    # Join matched words and unmatched text with a space\n",
+    "    result = ' '.join(matched_words)\n",
+    "    return result\n",
+    "    \n",
+    "text = \"जीरोएकदोतीनचारपांचछहसातआठनौदसजीरोएकदोतीनचारपांच\"\n",
+    "\n",
+    "if __name__==\"__main__\":\n",
+    "    converted=convert_to_list(text, text_to_list())\n",
+    "    print(converted)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "f6655a7c-7481-4a73-a2e6-5327f589bb8b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "जीरो तीन तीन चार र\n"
+     ]
+    }
+   ],
+   "source": [
+    "# # import nbimporter\n",
+    "# import nbimporter\n",
+    "# from Text2List import text_to_list\n",
+    "# def convert_to_list(text, text_list):\n",
+    "#     matched_words = []\n",
+    "#     unmatched_text = ''  # To accumulate unmatched characters\n",
+    "\n",
+    "#     # Sort text_list by length in descending order to prioritize longest matches first\n",
+    "#     text_list_sorted = sorted(text_list, key=len, reverse=True)\n",
+    "\n",
+    "#     while text:\n",
+    "#         matched = False\n",
+    "#         for word in text_list_sorted:\n",
+    "#             if word in text:\n",
+    "#                 # Add any accumulated unmatched text before appending the matched word\n",
+    "#                 if unmatched_text:\n",
+    "#                     matched_words.append(unmatched_text)\n",
+    "#                     unmatched_text = ''  # Reset unmatched text accumulator\n",
+    "\n",
+    "#                 matched_words.append(word)\n",
+    "#                 text = text[len(word):]  # Remove the matched part from text\n",
+    "#                 matched = True\n",
+    "#                 break\n",
+    "\n",
+    "#         if not matched:\n",
+    "#             # Accumulate unmatched characters\n",
+    "#             unmatched_text += text[0]\n",
+    "#             text = text[1:]\n",
+    "\n",
+    "#     # If there's any remaining unmatched text, add it to the result\n",
+    "#     if unmatched_text:\n",
+    "#         matched_words.append(unmatched_text)\n",
+    "\n",
+    "#     # Join matched words and unmatched text with a space\n",
+    "#     result = ' '.join(matched_words)\n",
+    "#     return result\n",
+    "    \n",
+    "# text = \"जीरोएकदोतीनचार\"\n",
+    "\n",
+    "# if __name__==\"__main__\":\n",
+    "#     converted=convert_to_list(text, text_to_list())\n",
+    "#     print(converted)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "26b725cd-d14f-4d8a-9829-99a7b9a5eeb3",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

gradio_hindi_number_conversion.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "bb78ac37-de4f-407a-8fd5-1a269fd937c9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Import necessary libraries and filter warnings\n",
+    "import warnings\n",
+    "warnings.filterwarnings(\"ignore\")\n",
+    "import nbimporter\n",
+    "import os\n",
+    "import re\n",
+    "import numpy as np\n",
+    "import torchaudio\n",
+    "from transformers import pipeline\n",
+    "from text2int import text_to_int\n",
+    "from isNumber import is_number\n",
+    "from Text2List import text_to_list\n",
+    "from convert2list import convert_to_list\n",
+    "from processDoubles import process_doubles\n",
+    "from replaceWords import replace_words\n",
+    "transcriber = pipeline(task=\"automatic-speech-recognition\", model=\"cdactvm/w2v-bert-2.0-hindi_v1\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "02b787e8-6d08-4351-a830-7f7cae7f8243",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import gradio as gr\n",
+    "\n",
+    "def transcribe(audio):\n",
+    "    # # Process the audio file\n",
+    "    transcript = transcriber(audio)\n",
+    "    text_value = transcript['text']\n",
+    "    print(text_value)\n",
+    "    processd_doubles=process_doubles(text_value)\n",
+    "    converted_to_list=convert_to_list(processd_doubles,text_to_list())\n",
+    "    replaced_words = replace_words(converted_to_list)\n",
+    "    converted_text=text_to_int(replaced_words)\n",
+    "    return converted_text\n",
+    "\n",
+    "\n",
+    "demo = gr.Interface(\n",
+    "    transcribe,\n",
+    "    gr.Audio(sources=\"microphone\", type=\"filepath\"),\n",
+    "    \"text\",\n",
+    ")\n",
+    "\n",
+    "demo.launch()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "756c0b55-17b4-4aa0-baac-d8f1c4b003df",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

isNumber.ipynb

@@ -0,0 +1,43 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ac442c1a-b404-4936-afec-7e4eb43bb68b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Function to check if the string is a number\n",
+    "def is_number(x):\n",
+    "    if type(x) == str:\n",
+    "        x = x.replace(',', '')\n",
+    "    try:\n",
+    "        float(x)\n",
+    "    except:\n",
+    "        return False\n",
+    "    return True"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

main.ipynb

@@ -0,0 +1,134 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "54bbfa73-b27d-44a0-895c-81c4d7b3ed7e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: nbimporter in c:\\users\\wchl\\anaconda3\\envs\\speech_analysis\\lib\\site-packages (0.3.4)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install nbimporter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "79a3e8c9-559a-4356-9c39-c4abb09ca60d",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "RuntimeError",
+     "evalue": "Failed to import transformers.pipelines because of the following error (look up to see its traceback):\nDescriptors cannot be created directly.\nIf this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.\nIf you cannot immediately regenerate your protos, some other possible workarounds are:\n 1. Downgrade the protobuf package to 3.20.x or lower.\n 2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).\n\nMore information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\transformers\\utils\\import_utils.py:1390\u001b[0m, in \u001b[0;36m_LazyModule._get_module\u001b[1;34m(self, module_name)\u001b[0m\n\u001b[0;32m   1389\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m-> 1390\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mimportlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mimport_module\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mmodule_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;18;43m__name__\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1391\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\importlib\\__init__.py:127\u001b[0m, in \u001b[0;36mimport_module\u001b[1;34m(name, package)\u001b[0m\n\u001b[0;32m    126\u001b[0m         level \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m--> 127\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_bootstrap\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_gcd_import\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m[\u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m:\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpackage\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m<frozen importlib._bootstrap>:1030\u001b[0m, in \u001b[0;36m_gcd_import\u001b[1;34m(name, package, level)\u001b[0m\n",
+      "File \u001b[1;32m<frozen importlib._bootstrap>:1007\u001b[0m, in \u001b[0;36m_find_and_load\u001b[1;34m(name, import_)\u001b[0m\n",
+      "File \u001b[1;32m<frozen importlib._bootstrap>:986\u001b[0m, in \u001b[0;36m_find_and_load_unlocked\u001b[1;34m(name, import_)\u001b[0m\n",
+      "File \u001b[1;32m<frozen importlib._bootstrap>:680\u001b[0m, in \u001b[0;36m_load_unlocked\u001b[1;34m(spec)\u001b[0m\n",
+      "File \u001b[1;32m<frozen importlib._bootstrap_external>:850\u001b[0m, in \u001b[0;36mexec_module\u001b[1;34m(self, module)\u001b[0m\n",
+      "File \u001b[1;32m<frozen importlib._bootstrap>:228\u001b[0m, in \u001b[0;36m_call_with_frames_removed\u001b[1;34m(f, *args, **kwds)\u001b[0m\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\transformers\\pipelines\\__init__.py:26\u001b[0m\n\u001b[0;32m     25\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_extraction_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m PreTrainedFeatureExtractor\n\u001b[1;32m---> 26\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimage_processing_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m BaseImageProcessor\n\u001b[0;32m     27\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodels\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mauto\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mconfiguration_auto\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoConfig\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\transformers\\image_processing_utils.py:28\u001b[0m\n\u001b[0;32m     27\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_extraction_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m BatchFeature \u001b[38;5;28;01mas\u001b[39;00m BaseBatchFeature\n\u001b[1;32m---> 28\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimage_transforms\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m center_crop, normalize, rescale\n\u001b[0;32m     29\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimage_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m ChannelDimension\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\transformers\\image_transforms.py:47\u001b[0m\n\u001b[0;32m     46\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_tf_available():\n\u001b[1;32m---> 47\u001b[0m     \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mtf\u001b[39;00m\n\u001b[0;32m     49\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_flax_available():\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\tensorflow\\__init__.py:37\u001b[0m\n\u001b[0;32m     35\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtyping\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01m_typing\u001b[39;00m\n\u001b[1;32m---> 37\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mtools\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m module_util \u001b[38;5;28;01mas\u001b[39;00m _module_util\n\u001b[0;32m     38\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutil\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlazy_loader\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m LazyLoader \u001b[38;5;28;01mas\u001b[39;00m _LazyLoader\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\tensorflow\\python\\__init__.py:37\u001b[0m\n\u001b[0;32m     36\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m pywrap_tensorflow \u001b[38;5;28;01mas\u001b[39;00m _pywrap_tensorflow\n\u001b[1;32m---> 37\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpython\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01meager\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m context\n\u001b[0;32m     39\u001b[0m \u001b[38;5;66;03m# pylint: enable=wildcard-import\u001b[39;00m\n\u001b[0;32m     40\u001b[0m \n\u001b[0;32m     41\u001b[0m \u001b[38;5;66;03m# Bring in subpackages.\u001b[39;00m\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\tensorflow\\python\\eager\\context.py:29\u001b[0m\n\u001b[0;32m     27\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01msix\u001b[39;00m\n\u001b[1;32m---> 29\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m function_pb2\n\u001b[0;32m     30\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mprotobuf\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m config_pb2\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\tensorflow\\core\\framework\\function_pb2.py:16\u001b[0m\n\u001b[0;32m     13\u001b[0m _sym_db \u001b[38;5;241m=\u001b[39m _symbol_database\u001b[38;5;241m.\u001b[39mDefault()\n\u001b[1;32m---> 16\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m attr_value_pb2 \u001b[38;5;28;01mas\u001b[39;00m tensorflow_dot_core_dot_framework_dot_attr__value__pb2\n\u001b[0;32m     17\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m node_def_pb2 \u001b[38;5;28;01mas\u001b[39;00m tensorflow_dot_core_dot_framework_dot_node__def__pb2\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\tensorflow\\core\\framework\\attr_value_pb2.py:16\u001b[0m\n\u001b[0;32m     13\u001b[0m _sym_db \u001b[38;5;241m=\u001b[39m _symbol_database\u001b[38;5;241m.\u001b[39mDefault()\n\u001b[1;32m---> 16\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tensor_pb2 \u001b[38;5;28;01mas\u001b[39;00m tensorflow_dot_core_dot_framework_dot_tensor__pb2\n\u001b[0;32m     17\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tensor_shape_pb2 \u001b[38;5;28;01mas\u001b[39;00m tensorflow_dot_core_dot_framework_dot_tensor__shape__pb2\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\tensorflow\\core\\framework\\tensor_pb2.py:16\u001b[0m\n\u001b[0;32m     13\u001b[0m _sym_db \u001b[38;5;241m=\u001b[39m _symbol_database\u001b[38;5;241m.\u001b[39mDefault()\n\u001b[1;32m---> 16\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m resource_handle_pb2 \u001b[38;5;28;01mas\u001b[39;00m tensorflow_dot_core_dot_framework_dot_resource__handle__pb2\n\u001b[0;32m     17\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tensor_shape_pb2 \u001b[38;5;28;01mas\u001b[39;00m tensorflow_dot_core_dot_framework_dot_tensor__shape__pb2\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\tensorflow\\core\\framework\\resource_handle_pb2.py:16\u001b[0m\n\u001b[0;32m     13\u001b[0m _sym_db \u001b[38;5;241m=\u001b[39m _symbol_database\u001b[38;5;241m.\u001b[39mDefault()\n\u001b[1;32m---> 16\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m tensor_shape_pb2 \u001b[38;5;28;01mas\u001b[39;00m tensorflow_dot_core_dot_framework_dot_tensor__shape__pb2\n\u001b[0;32m     17\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mframework\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m types_pb2 \u001b[38;5;28;01mas\u001b[39;00m tensorflow_dot_core_dot_framework_dot_types__pb2\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\tensorflow\\core\\framework\\tensor_shape_pb2.py:36\u001b[0m\n\u001b[0;32m     18\u001b[0m DESCRIPTOR \u001b[38;5;241m=\u001b[39m _descriptor\u001b[38;5;241m.\u001b[39mFileDescriptor(\n\u001b[0;32m     19\u001b[0m   name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtensorflow/core/framework/tensor_shape.proto\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m     20\u001b[0m   package\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtensorflow\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     23\u001b[0m   serialized_pb\u001b[38;5;241m=\u001b[39m_b(\u001b[38;5;124m'\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m,tensorflow/core/framework/tensor_shape.proto\u001b[39m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mtensorflow\u001b[39m\u001b[38;5;130;01m\\\"\u001b[39;00m\u001b[38;5;124mz\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x10\u001b[39;00m\u001b[38;5;124mTensorShapeProto\u001b[39m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;124m-\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x03\u001b[39;00m\u001b[38;5;130;01m\\x64\u001b[39;00m\u001b[38;5;124mim\u001b[39m\u001b[38;5;130;01m\\x18\u001b[39;00m\u001b[38;5;130;01m\\x02\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;130;01m\\x03\u001b[39;00m\u001b[38;5;124m(\u001b[39m\u001b[38;5;130;01m\\x0b\u001b[39;00m\u001b[38;5;130;01m\\x32\u001b[39;00m\u001b[38;5;124m .tensorflow.TensorShapeProto.Dim\u001b[39m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\x14\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x0c\u001b[39;00m\u001b[38;5;124munknown_rank\u001b[39m\u001b[38;5;130;01m\\x18\u001b[39;00m\u001b[38;5;130;01m\\x03\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;130;01m\\x01\u001b[39;00m\u001b[38;5;124m(\u001b[39m\u001b[38;5;130;01m\\x08\u001b[39;00m\u001b[38;5;130;01m\\x1a\u001b[39;00m\u001b[38;5;124m!\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x03\u001b[39;00m\u001b[38;5;130;01m\\x44\u001b[39;00m\u001b[38;5;124mim\u001b[39m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\x0c\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x04\u001b[39;00m\u001b[38;5;124msize\u001b[39m\u001b[38;5;130;01m\\x18\u001b[39;00m\u001b[38;5;130;01m\\x01\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;130;01m\\x01\u001b[39;00m\u001b[38;5;124m(\u001b[39m\u001b[38;5;130;01m\\x03\u001b[39;00m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\x0c\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x04\u001b[39;00m\u001b[38;5;124mname\u001b[39m\u001b[38;5;130;01m\\x18\u001b[39;00m\u001b[38;5;130;01m\\x02\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;130;01m\\x01\u001b[39;00m\u001b[38;5;124m(\u001b[39m\u001b[38;5;130;01m\\t\u001b[39;00m\u001b[38;5;124mB\u001b[39m\u001b[38;5;130;01m\\x87\u001b[39;00m\u001b[38;5;130;01m\\x01\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x18\u001b[39;00m\u001b[38;5;124morg.tensorflow.frameworkB\u001b[39m\u001b[38;5;130;01m\\x11\u001b[39;00m\u001b[38;5;124mTensorShapeProtosP\u001b[39m\u001b[38;5;130;01m\\x01\u001b[39;00m\u001b[38;5;124mZSgithub.com/tensorflow/tensorflow/tensorflow/go/core/framework/tensor_shape_go_proto\u001b[39m\u001b[38;5;130;01m\\xf8\u001b[39;00m\u001b[38;5;130;01m\\x01\u001b[39;00m\u001b[38;5;130;01m\\x01\u001b[39;00m\u001b[38;5;130;01m\\x62\u001b[39;00m\u001b[38;5;130;01m\\x06\u001b[39;00m\u001b[38;5;124mproto3\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m     24\u001b[0m )\n\u001b[0;32m     29\u001b[0m _TENSORSHAPEPROTO_DIM \u001b[38;5;241m=\u001b[39m _descriptor\u001b[38;5;241m.\u001b[39mDescriptor(\n\u001b[0;32m     30\u001b[0m   name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mDim\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m     31\u001b[0m   full_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtensorflow.TensorShapeProto.Dim\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m     32\u001b[0m   filename\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m     33\u001b[0m   file\u001b[38;5;241m=\u001b[39mDESCRIPTOR,\n\u001b[0;32m     34\u001b[0m   containing_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m     35\u001b[0m   fields\u001b[38;5;241m=\u001b[39m[\n\u001b[1;32m---> 36\u001b[0m     \u001b[43m_descriptor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mFieldDescriptor\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m     37\u001b[0m \u001b[43m      \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43msize\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfull_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mtensorflow.TensorShapeProto.Dim.size\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindex\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m     38\u001b[0m \u001b[43m      \u001b[49m\u001b[43mnumber\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mtype\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcpp_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m2\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlabel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m     39\u001b[0m \u001b[43m      \u001b[49m\u001b[43mhas_default_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdefault_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m     40\u001b[0m \u001b[43m      \u001b[49m\u001b[43mmessage_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43menum_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcontaining_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m     41\u001b[0m \u001b[43m      \u001b[49m\u001b[43mis_extension\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextension_scope\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[0;32m     42\u001b[0m \u001b[43m      \u001b[49m\u001b[43mserialized_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfile\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mDESCRIPTOR\u001b[49m\u001b[43m)\u001b[49m,\n\u001b[0;32m     43\u001b[0m     _descriptor\u001b[38;5;241m.\u001b[39mFieldDescriptor(\n\u001b[0;32m     44\u001b[0m       name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m'\u001b[39m, full_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtensorflow.TensorShapeProto.Dim.name\u001b[39m\u001b[38;5;124m'\u001b[39m, index\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m,\n\u001b[0;32m     45\u001b[0m       number\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m2\u001b[39m, \u001b[38;5;28mtype\u001b[39m\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m9\u001b[39m, cpp_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m9\u001b[39m, label\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m,\n\u001b[0;32m     46\u001b[0m       has_default_value\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, default_value\u001b[38;5;241m=\u001b[39m_b(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mdecode(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mutf-8\u001b[39m\u001b[38;5;124m'\u001b[39m),\n\u001b[0;32m     47\u001b[0m       message_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, enum_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, containing_type\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m     48\u001b[0m       is_extension\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, extension_scope\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m     49\u001b[0m       serialized_options\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, file\u001b[38;5;241m=\u001b[39mDESCRIPTOR),\n\u001b[0;32m     50\u001b[0m   ],\n\u001b[0;32m     51\u001b[0m   extensions\u001b[38;5;241m=\u001b[39m[\n\u001b[0;32m     52\u001b[0m   ],\n\u001b[0;32m     53\u001b[0m   nested_types\u001b[38;5;241m=\u001b[39m[],\n\u001b[0;32m     54\u001b[0m   enum_types\u001b[38;5;241m=\u001b[39m[\n\u001b[0;32m     55\u001b[0m   ],\n\u001b[0;32m     56\u001b[0m   serialized_options\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m     57\u001b[0m   is_extendable\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m     58\u001b[0m   syntax\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mproto3\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m     59\u001b[0m   extension_ranges\u001b[38;5;241m=\u001b[39m[],\n\u001b[0;32m     60\u001b[0m   oneofs\u001b[38;5;241m=\u001b[39m[\n\u001b[0;32m     61\u001b[0m   ],\n\u001b[0;32m     62\u001b[0m   serialized_start\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m149\u001b[39m,\n\u001b[0;32m     63\u001b[0m   serialized_end\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m182\u001b[39m,\n\u001b[0;32m     64\u001b[0m )\n\u001b[0;32m     66\u001b[0m _TENSORSHAPEPROTO \u001b[38;5;241m=\u001b[39m _descriptor\u001b[38;5;241m.\u001b[39mDescriptor(\n\u001b[0;32m     67\u001b[0m   name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mTensorShapeProto\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m     68\u001b[0m   full_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtensorflow.TensorShapeProto\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    100\u001b[0m   serialized_end\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m182\u001b[39m,\n\u001b[0;32m    101\u001b[0m )\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\google\\protobuf\\descriptor.py:621\u001b[0m, in \u001b[0;36mFieldDescriptor.__new__\u001b[1;34m(cls, name, full_name, index, number, type, cpp_type, label, default_value, message_type, enum_type, containing_type, is_extension, extension_scope, options, serialized_options, has_default_value, containing_oneof, json_name, file, create_key)\u001b[0m\n\u001b[0;32m    615\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__new__\u001b[39m(\u001b[38;5;28mcls\u001b[39m, name, full_name, index, number, \u001b[38;5;28mtype\u001b[39m, cpp_type, label,\n\u001b[0;32m    616\u001b[0m             default_value, message_type, enum_type, containing_type,\n\u001b[0;32m    617\u001b[0m             is_extension, extension_scope, options\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m    618\u001b[0m             serialized_options\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m    619\u001b[0m             has_default_value\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, containing_oneof\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, json_name\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m    620\u001b[0m             file\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, create_key\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):  \u001b[38;5;66;03m# pylint: disable=redefined-builtin\u001b[39;00m\n\u001b[1;32m--> 621\u001b[0m   \u001b[43m_message\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mMessage\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_CheckCalledFromGeneratedFile\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    622\u001b[0m   \u001b[38;5;28;01mif\u001b[39;00m is_extension:\n",
+      "\u001b[1;31mTypeError\u001b[0m: Descriptors cannot be created directly.\nIf this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.\nIf you cannot immediately regenerate your protos, some other possible workarounds are:\n 1. Downgrade the protobuf package to 3.20.x or lower.\n 2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).\n\nMore information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates",
+      "\nThe above exception was the direct cause of the following exception:\n",
+      "\u001b[1;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[2], line 8\u001b[0m\n\u001b[0;32m      6\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mre\u001b[39;00m\n\u001b[0;32m      7\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorchaudio\u001b[39;00m\n\u001b[1;32m----> 8\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m pipeline\n\u001b[0;32m      9\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtext2int\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m text_to_int\n\u001b[0;32m     10\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01misNumber\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m is_number\n",
+      "File \u001b[1;32m<frozen importlib._bootstrap>:1055\u001b[0m, in \u001b[0;36m_handle_fromlist\u001b[1;34m(module, fromlist, import_, recursive)\u001b[0m\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\transformers\\utils\\import_utils.py:1380\u001b[0m, in \u001b[0;36m_LazyModule.__getattr__\u001b[1;34m(self, name)\u001b[0m\n\u001b[0;32m   1378\u001b[0m     value \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_module(name)\n\u001b[0;32m   1379\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m name \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_class_to_module\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[1;32m-> 1380\u001b[0m     module \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_module\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_class_to_module\u001b[49m\u001b[43m[\u001b[49m\u001b[43mname\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1381\u001b[0m     value \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(module, name)\n\u001b[0;32m   1382\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
+      "File \u001b[1;32m~\\anaconda3\\envs\\Speech_Analysis\\lib\\site-packages\\transformers\\utils\\import_utils.py:1392\u001b[0m, in \u001b[0;36m_LazyModule._get_module\u001b[1;34m(self, module_name)\u001b[0m\n\u001b[0;32m   1390\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m importlib\u001b[38;5;241m.\u001b[39mimport_module(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m module_name, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m)\n\u001b[0;32m   1391\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m-> 1392\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\n\u001b[0;32m   1393\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFailed to import \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmodule_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m because of the following error (look up to see its\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   1394\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m traceback):\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   1395\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n",
+      "\u001b[1;31mRuntimeError\u001b[0m: Failed to import transformers.pipelines because of the following error (look up to see its traceback):\nDescriptors cannot be created directly.\nIf this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.\nIf you cannot immediately regenerate your protos, some other possible workarounds are:\n 1. Downgrade the protobuf package to 3.20.x or lower.\n 2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).\n\nMore information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates"
+     ]
+    }
+   ],
+   "source": [
+    "# Import necessary libraries and filter warnings\n",
+    "import warnings\n",
+    "warnings.filterwarnings(\"ignore\")\n",
+    "import nbimporter\n",
+    "import os\n",
+    "import re\n",
+    "import torchaudio\n",
+    "from transformers import pipeline\n",
+    "from text2int import text_to_int\n",
+    "from isNumber import is_number\n",
+    "from Text2List import text_to_list\n",
+    "from convert2list import convert_to_list\n",
+    "from processDoubles import process_doubles\n",
+    "from replaceWords import replace_words\n",
+    "pipe = pipeline(task=\"automatic-speech-recognition\", model=\"cdactvm/w2v-bert-2.0-hindi_v1\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6075c345-ee6a-4810-b02f-88d517d272e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# # Process the audio file\n",
+    "transcript = pipe(\"C:/Users/WCHL/Desktop/hindi_dataset/train/hindi_numbers_test/hindi7.mp3\")\n",
+    "text_value = transcript['text']\n",
+    "processd_doubles=process_doubles(text_value)\n",
+    "converted_to_list=convert_to_list(processd_doubles,text_to_list())\n",
+    "replaced_words = replace_words(converted_to_list)\n",
+    "converted_text=text_to_int(replaced_words)\n",
+    "print(f\"generated text    : {text_value}\")\n",
+    "print(f\"processed doubles : {processd_doubles}\")\n",
+    "print(f\"converted to list : {converted_to_list}\")\n",
+    "print(f\"replaced words    : {replaced_words}\")\n",
+    "print(f\"final text        : {converted_text}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "45040aca-7564-4b07-8e13-1fde7f4f8da2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

numberMapping.ipynb

@@ -0,0 +1,162 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f170db4-bc35-4f00-9c10-25ae297beda5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "replacement_map = {\n",
+    "    'zero': ['शून्य', 'जेरो', 'शुन्ना', 'जीरो'],\n",
+    "    'one': ['वन', 'एंक', 'इक', 'एक'],\n",
+    "    'two': ['टू', 'दौ', 'दो'],\n",
+    "    'three': ['थ्री', 'तीना', 'तीन', 'त्री'],\n",
+    "    'four': ['फोर', 'फॉर', 'च्यार', 'चार'],\n",
+    "    'five': ['फाइव', 'पाँच', 'पांच'],\n",
+    "    'six': ['सिक्स', 'चह', 'छौ', 'छै', 'छह'],\n",
+    "    'seven': ['सेवन', 'सात'],\n",
+    "    'eight': ['एट', 'अट', 'आठ'],\n",
+    "    'nine': ['नाइन', 'नौ'],\n",
+    "    'ten': ['टेन', 'दस'],\n",
+    "    \n",
+    "    # Numbers from 11 to 19\n",
+    "    'eleven': ['इलेवन', 'ग्यारह'],\n",
+    "    'twelve': ['ट्वेल्व', 'बारह'],\n",
+    "    'thirteen': ['थर्टीन', 'तेरह'],\n",
+    "    'fourteen': ['फोर्टीन', 'चौदह'],\n",
+    "    'fifteen': ['फिफ्टीन', 'पंद्रह'],\n",
+    "    'sixteen': ['सिक्स्टीन', 'सोलह'],\n",
+    "    'seventeen': ['सेवंटीन', 'सत्रह'],\n",
+    "    'eighteen': ['एटीन', 'अठारह'],\n",
+    "    'nineteen': ['नाइनटीन', 'उन्नीस'],\n",
+    "\n",
+    "    # Multiples of ten\n",
+    "    'twenty': ['ट्वेंटी', 'बीस'],\n",
+    "    'thirty': ['थर्टी', 'तीस'],\n",
+    "    'forty': ['फोर्टी', 'चालीस'],\n",
+    "    'fifty': ['फिफ्टी', 'पचास'],\n",
+    "    'sixty': ['सिक्स्टी', 'साठ'],\n",
+    "    'seventy': ['सेवंटी', 'सत्तर'],\n",
+    "    'eighty': ['एटी', 'अस्सी'],\n",
+    "    'ninety': ['नाइंटी', 'नब्बे'],\n",
+    "\n",
+    "    # Numbers from 21 to 29\n",
+    "    'twenty one': ['ट्वेंटी वन', 'इक्कीस'],\n",
+    "    'twenty two': ['ट्वेंटी टू', 'बाईस'],\n",
+    "    'twenty three': ['ट्वेंटी थ्री', 'तेईस'],\n",
+    "    'twenty four': ['ट्वेंटी फोर', 'चौबीस'],\n",
+    "    'twenty five': ['ट्वेंटी फाइव', 'पच्चीस'],\n",
+    "    'twenty six': ['ट्वेंटी सिक्स', 'छब्बीस'],\n",
+    "    'twenty seven': ['ट्वेंटी सेवन', 'सत्ताईस'],\n",
+    "    'twenty eight': ['ट्वेंटी एट', 'अट्ठाईस'],\n",
+    "    'twenty nine': ['ट्वेंटी नाइन', 'उनतीस'],\n",
+    "\n",
+    "    # Numbers from 31 to 39\n",
+    "    'thirty one': ['थर्टी वन', 'इकतीस'],\n",
+    "    'thirty two': ['थर्टी टू', 'बत्तीस'],\n",
+    "    'thirty three': ['थर्टी थ्री', 'तेतीस'],\n",
+    "    'thirty four': ['थर्टी फोर', 'चौंतीस'],\n",
+    "    'thirty five': ['थर्टी फाइव', 'पैंतीस'],\n",
+    "    'thirty six': ['थर्टी सिक्स', 'छत्तीस'],\n",
+    "    'thirty seven': ['थर्टी सेवन', 'सैंतीस'],\n",
+    "    'thirty eight': ['थर्टी एट', 'अड़तीस'],\n",
+    "    'thirty nine': ['थर्टी नाइन', 'उनतालीस'],\n",
+    "\n",
+    "    # Numbers from 41 to 49\n",
+    "    'forty one': ['फोर्टी वन', 'इकतालीस'],\n",
+    "    'forty two': ['फोर्टी टू', 'बयालीस'],\n",
+    "    'forty three': ['फोर्टी थ्री', 'तैंतालीस'],\n",
+    "    'forty four': ['फोर्टी फोर', 'चौंतालीस'],\n",
+    "    'forty five': ['फोर्टी फाइव', 'पैंतालीस'],\n",
+    "    'forty six': ['फोर्टी सिक्स', 'छयालिस'],\n",
+    "    'forty seven': ['फोर्टी सेवन', 'सैंतालीस'],\n",
+    "    'forty eight': ['फोर्टी एट', 'अड़तालीस'],\n",
+    "    'forty nine': ['फोर्टी नाइन', 'उनचास'],\n",
+    "\n",
+    "    # Numbers from 51 to 59\n",
+    "    'fifty one': ['फिफ्टी वन', 'इक्यावन'],\n",
+    "    'fifty two': ['फिफ्टी टू', 'बावन'],\n",
+    "    'fifty three': ['फिफ्टी थ्री', 'तिरेपन'],\n",
+    "    'fifty four': ['फिफ्टी फोर', 'चौवन'],\n",
+    "    'fifty five': ['फिफ्टी फाइव', 'पचपन'],\n",
+    "    'fifty six': ['फिफ्टी सिक्स', 'छप्पन'],\n",
+    "    'fifty seven': ['फिफ्टी सेवन', 'सत्तावन'],\n",
+    "    'fifty eight': ['फिफ्टी एट', 'अट्ठावन'],\n",
+    "    'fifty nine': ['फिफ्टी नाइन', 'उनसठ'],\n",
+    "\n",
+    "    # Numbers from 61 to 69\n",
+    "    'sixty one': ['सिक्स्टी वन', 'इकसठ'],\n",
+    "    'sixty two': ['सिक्स्टी टू', 'बासठ'],\n",
+    "    'sixty three': ['सिक्स्टी थ्री', 'तिरसठ'],\n",
+    "    'sixty four': ['सिक्स्टी फोर', 'चौंसठ'],\n",
+    "    'sixty five': ['सिक्स्टी फाइव', 'पैंसठ'],\n",
+    "    'sixty six': ['सिक्स्टी सिक्स', 'छियासठ'],\n",
+    "    'sixty seven': ['सिक्स्टी सेवन', 'सड़सठ'],\n",
+    "    'sixty eight': ['सिक्स्टी एट', 'अड़सठ'],\n",
+    "    'sixty nine': ['सिक्स्टी नाइन', 'उनहत्तर'],\n",
+    "\n",
+    "    # Numbers from 71 to 79\n",
+    "    'seventy one': ['सेवंटी वन', 'इकहत्तर'],\n",
+    "    'seventy two': ['सेवंटी टू', 'बहत्तर'],\n",
+    "    'seventy three': ['सेवंटी थ्री', 'तिहत्तर'],\n",
+    "    'seventy four': ['सेवंटी फोर', 'चौहत्तर'],\n",
+    "    'seventy five': ['सेवंटी फाइव', 'पचहत्तर'],\n",
+    "    'seventy six': ['सेवंटी सिक्स', 'छिहत्तर'],\n",
+    "    'seventy seven': ['सेवंटी सेवन', 'सतहत्तर'],\n",
+    "    'seventy eight': ['सेवंटी एट', 'अठहत्तर'],\n",
+    "    'seventy nine': ['सेवंटी नाइन', 'उन्यासी'],\n",
+    "\n",
+    "    # Numbers from 81 to 89\n",
+    "    'eighty one': ['एटी वन', 'इक्यासी'],\n",
+    "    'eighty two': ['एटी टू', 'बयासी'],\n",
+    "    'eighty three': ['एटी थ्री', 'तिरासी'],\n",
+    "    'eighty four': ['एटी फोर', 'चौरासी'],\n",
+    "    'eighty five': ['एटी फाइव', 'पचासी'],\n",
+    "    'eighty six': ['एटी सिक्स', 'छियासी'],\n",
+    "    'eighty seven': ['एटी सेवन', 'सतासी'],\n",
+    "    'eighty eight': ['एटी एट', 'अठासी'],\n",
+    "    'eighty nine': ['एटी नाइन', 'नवासी'],\n",
+    "\n",
+    "    # Numbers from 91 to 99\n",
+    "    'ninety one': ['नाइंटी वन', 'इक्यानवे'],\n",
+    "    'ninety two': ['नाइंटी टू', 'बानवे'],\n",
+    "    'ninety three': ['नाइंटी थ्री', 'तिरानवे'],\n",
+    "    'ninety four': ['नाइंटी फोर', 'चौरानवे'],\n",
+    "    'ninety five': ['नाइंटी फाइव', 'पचानवे'],\n",
+    "    'ninety six': ['नाइंटी सिक्स', 'छियानवे'],\n",
+    "    'ninety seven': ['नाइंटी सेवन', 'सतानवे'],\n",
+    "    'ninety eight': ['नाइंटी एट', 'अठानवे'],\n",
+    "    'ninety nine': ['नाइंटी नाइन', 'निन्यानवे'],\n",
+    "\n",
+    "    # Hundred\n",
+    "    'hundred': ['हंड्रेड', 'सौ'],\n",
+    "\n",
+    "    # Special for double digits\n",
+    "    'डबल': ['दबल', 'डबल', 'दुबाल'],\n",
+    "}\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

processDoubles.ipynb

@@ -0,0 +1,52 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5912ba94-833f-4662-8b8c-f201b5dde892",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Function to process \"double\" followed by a number\n",
+    "def process_doubles(sentence):\n",
+    "    tokens = sentence.split()\n",
+    "    result = []\n",
+    "    i = 0\n",
+    "    while i < len(tokens):\n",
+    "        if tokens[i] == \"डबल\":\n",
+    "            if i + 1 < len(tokens):\n",
+    "                result.append(tokens[i + 1])\n",
+    "                result.append(tokens[i + 1])\n",
+    "                i += 2\n",
+    "            else:\n",
+    "                result.append(tokens[i])\n",
+    "                i += 1\n",
+    "        else:\n",
+    "            result.append(tokens[i])\n",
+    "            i += 1\n",
+    "    return ' '.join(result)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

replaceWords.ipynb

@@ -0,0 +1,188 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "19bbb494-3054-48ae-9b64-7f0756c0532d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "\n",
+    "def replace_words(sentence):\n",
+    "    # Define a dictionary mapping a single word to a list of words or phrases\n",
+    "    replacement_map = {\n",
+    "    # Multiples of ten\n",
+    "    'twenty': ['ट्वेंटी', 'बीस'],\n",
+    "    'thirty': ['थर्टी', 'तीस'],\n",
+    "    'forty': ['फोर्टी', 'चालीस'],\n",
+    "    'fifty': ['फिफ्टी', 'पचास'],\n",
+    "    'sixty': ['सिक्स्टी', 'साठ'],\n",
+    "    'seventy': ['सेवंटी', 'सत्तर','सेवनटी','सेवेनटी','सेवांटी'],\n",
+    "    'eighty': ['एटी', 'अस्सी'],\n",
+    "    'ninety': ['नाइंटी', 'नब्बे'],\n",
+    "    \n",
+    "    # Numbers from 11 to 19\n",
+    "    'eleven': ['इलेवन', 'ग्यारह','इगारा'],\n",
+    "    'twelve': ['ट्वेल्व', 'बारह'],\n",
+    "    'thirteen': ['थर्टीन', 'तेरह','तेरा'],\n",
+    "    'fourteen': ['फोर्टीन', 'चौदह'],\n",
+    "    'fifteen': ['फिफ्टीन', 'पंद्रह','पंद्रा'],\n",
+    "    'sixteen': ['सिक्स्टीन', 'सोलह','सोल्ला'],\n",
+    "    'seventeen': ['सेवंटीन', 'सत्रह''सतरा'],\n",
+    "    'eighteen': ['एटीन', 'अठारह''अठारा'],\n",
+    "    'nineteen': ['नाइनटीन', 'उन्नीस','उन्नईस','उनाइस'],\n",
+    "\n",
+    "    # Numbers from 21 to 29\n",
+    "    'twenty one': ['ट्वेंटी वन', 'इक्कीस'],\n",
+    "    'twenty two': ['ट्वेंटी टू', 'बाईस'],\n",
+    "    'twenty three': ['ट्वेंटी थ्री', 'तेईस'],\n",
+    "    'twenty four': ['ट्वेंटी फोर', 'चौबीस'],\n",
+    "    'twenty five': ['ट्वेंटी फाइव', 'पच्चीस'],\n",
+    "    'twenty six': ['ट्वेंटी सिक्स', 'छब्बीस'],\n",
+    "    'twenty seven': ['ट्वेंटी सेवन', 'सत्ताईस','सताईस'],\n",
+    "    'twenty eight': ['ट्वेंटी एट', 'अट्ठाईस','अठ्ठाइस','अठ्ठाईस'],\n",
+    "    'twenty nine': ['ट्वेंटी नाइन', 'उनतीस'],\n",
+    "\n",
+    "    # Numbers from 31 to 39\n",
+    "    'thirty one': ['थर्टी वन', 'इकतीस'],\n",
+    "    'thirty two': ['थर्टी टू', 'बत्तीस'],\n",
+    "    'thirty three': ['थर्टी थ्री', 'तेतीस'],\n",
+    "    'thirty four': ['थर्टी फोर', 'चौंतीस'],\n",
+    "    'thirty five': ['थर्टी फाइव', 'पैंतीस'],\n",
+    "    'thirty six': ['थर्टी सिक्स', 'छत्तीस'],\n",
+    "    'thirty seven': ['थर्टी सेवन', 'सैंतीस'],\n",
+    "    'thirty eight': ['थर्टी एट', 'अड़तीस'],\n",
+    "    'thirty nine': ['थर्टी नाइन', 'उनतालीस'],\n",
+    "\n",
+    "    # Numbers from 41 to 49\n",
+    "    'forty one': ['फोर्टी वन', 'इकतालीस'],\n",
+    "    'forty two': ['फोर्टी टू', 'बयालीस'],\n",
+    "    'forty three': ['फोर्टी थ्री', 'तैंतालीस'],\n",
+    "    'forty four': ['फोर्टी फोर', 'चौंतालीस'],\n",
+    "    'forty five': ['फोर्टी फाइव', 'पैंतालीस'],\n",
+    "    'forty six': ['फोर्टी सिक्स', 'छयालिस'],\n",
+    "    'forty seven': ['फोर्टी सेवन', 'सैंतालीस'],\n",
+    "    'forty eight': ['फोर्टी एट', 'अड़तालीस'],\n",
+    "    'forty nine': ['फोर्टी नाइन', 'उनचास'],\n",
+    "\n",
+    "    # Numbers from 51 to 59\n",
+    "    'fifty one': ['फिफ्टी वन', 'इक्यावन'],\n",
+    "    'fifty two': ['फिफ्टी टू', 'बावन'],\n",
+    "    'fifty three': ['फिफ्टी थ्री', 'तिरेपन'],\n",
+    "    'fifty four': ['फिफ्टी फोर', 'चौवन'],\n",
+    "    'fifty five': ['फिफ्टी फाइव', 'पचपन'],\n",
+    "    'fifty six': ['फिफ्टी सिक्स', 'छप्पन','छपपन'],\n",
+    "    'fifty seven': ['फिफ्टी सेवन', 'सत्तावन','संताबन','संतावन'],\n",
+    "    'fifty eight': ['फिफ्टी एट', 'अट्��ावन','अंठावन'],\n",
+    "    'fifty nine': ['फिफ्टी नाइन', 'उनसठ','उंसट'],\n",
+    "\n",
+    "    # Numbers from 61 to 69\n",
+    "    'sixty one': ['सिक्स्टी वन', 'इकसठ'],\n",
+    "    'sixty two': ['सिक्स्टी टू', 'बासठ'],\n",
+    "    'sixty three': ['सिक्स्टी थ्री', 'तिरसठ'],\n",
+    "    'sixty four': ['सिक्स्टी फोर', 'चौंसठ'],\n",
+    "    'sixty five': ['सिक्स्टी फाइव', 'पैंसठ'],\n",
+    "    'sixty six': ['सिक्स्टी सिक्स', 'छियासठ'],\n",
+    "    'sixty seven': ['सिक्स्टी सेवन', 'सड़सठ'],\n",
+    "    'sixty eight': ['सिक्स्टी एट', 'अड़सठ'],\n",
+    "    'sixty nine': ['सिक्स्टी नाइन', 'उनहत्तर'],\n",
+    "\n",
+    "    # Numbers from 71 to 79\n",
+    "    'seventy one': ['सेवंटी वन', 'इकहत्तर','इखत्तर','इकत्तर'],\n",
+    "    'seventy two': ['सेवंटी टू', 'बहत्तर'],\n",
+    "    'seventy three': ['सेवंटी थ्री', 'तिहत्तर','तियत्र','तियत्तर','तीहत्तर','तिहत्थर'],\n",
+    "    'seventy four': ['सेवंटी फोर', 'चौहत्तर',],\n",
+    "    'seventy five': ['सेवंटी फाइव', 'पचहत्तर','पछत्तर','पिछत्तर','पचहत्तर','पचत्तर'],\n",
+    "    'seventy six': ['सेवंटी सिक्स', 'छिहत्तर','छीहत्तर'],\n",
+    "    'seventy seven': ['सेवंटी सेवन', 'सतहत्तर','सतात्तर','सतत्तर','सतहत्थर'],\n",
+    "    'seventy eight': ['सेवंटी एट', 'अठहत्तर','अठत्तर'],\n",
+    "    'seventy nine': ['सेवंटी नाइन', 'उन्यासी','उनासी'],\n",
+    "\n",
+    "    # Numbers from 81 to 89\n",
+    "    'eighty one': ['एटी वन', 'इक्यासी'],\n",
+    "    'eighty two': ['एटी टू', 'बयासी'],\n",
+    "    'eighty three': ['एटी थ्री', 'तिरासी'],\n",
+    "    'eighty four': ['एटी फोर', 'चौरासी'],\n",
+    "    'eighty five': ['एटी फाइव', 'पचासी'],\n",
+    "    'eighty six': ['एटी सिक्स', 'छियासी'],\n",
+    "    'eighty seven': ['एटी सेवन', 'सतासी'],\n",
+    "    'eighty eight': ['एटी एट', 'अठासी'],\n",
+    "    'eighty nine': ['एटी नाइन', 'नवासी'],\n",
+    "\n",
+    "    # Numbers from 91 to 99\n",
+    "    'ninety one': ['नाइंटी वन', 'इक्यानवे'],\n",
+    "    'ninety two': ['नाइंटी टू', 'बानवे'],\n",
+    "    'ninety three': ['नाइंटी थ्री', 'तिरानवे'],\n",
+    "    'ninety four': ['नाइंटी फोर', 'चौरानवे'],\n",
+    "    'ninety five': ['नाइंटी फाइव', 'पचानवे'],\n",
+    "    'ninety six': ['नाइंटी सिक्स', 'छियानवे'],\n",
+    "    'ninety seven': ['नाइंटी सेवन', 'सतानवे'],\n",
+    "    'ninety eight': ['नाइंटी एट', 'अठानवे'],\n",
+    "    'ninety nine': ['नाइंटी नाइन', 'निन्यानवे'],\n",
+    "    # Numbers from one to ten\n",
+    "    'seven': ['सेवन', 'सात'],\n",
+    "    'zero': ['शून्य', 'जेरो', 'शुन्ना', 'जीरो'],\n",
+    "    'one': ['वन', 'एंक', 'इक', 'एक'],\n",
+    "    'two': ['टू', 'दो'],\n",
+    "    'three': ['थ्री', 'तीना', 'तीन', 'त्री'],\n",
+    "    'four': ['फोर', 'फॉर', 'च्यार', 'चार'],\n",
+    "    'five': ['फाइव', 'पाँच', 'पांच'],\n",
+    "    'six': ['सिक्स', 'चह', 'छौ', 'छै', 'छह', 'छे'],\n",
+    "    'eight': ['एट', 'अट', 'आठ'],\n",
+    "    'nine': ['नाइन', 'नौ'],\n",
+    "    'ten': ['टेन', 'दस'],\n",
+    "    # Hundred\n",
+    "    'hundred': ['हंड्रेड', 'सौ','सो','साव'],\n",
+    "    # Thousand\n",
+    "    'thousand' : ['हजार','थौजनड','थाउजंड','हज़ार'],\n",
+    "    # Lakhs\n",
+    "    'lac' : ['लाख'],\n",
+    "\n",
+    "    # Special for double digits\n",
+    "    'डबल': ['दबल', 'डबल', 'दुबाल'],\n",
+    "    }\n",
+    "\n",
+    "    words = sentence.split()  # Split the sentence by spaces\n",
+    "\n",
+    "    # Replace words using the mapping\n",
+    "    for i, word in enumerate(words):\n",
+    "        for replacement, patterns in replacement_map.items():\n",
+    "            if word in patterns:\n",
+    "                words[i] = replacement  # Replace the word if it's fully matched\n",
+    "\n",
+    "    # Join the processed words back into a sentence\n",
+    "    return ' '.join(words)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7bdb593a-cb68-4b04-af8d-b61ea396a5eb",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

text2int.ipynb

@@ -0,0 +1,232 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "61185b34-45e0-4a78-a84b-2cedd08ad39a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# # Function to convert Hindi text to numerical representation\n",
+    "# from isNumber import is_number\n",
+    "\n",
+    "# def text_to_int (textnum, numwords={}):\n",
+    "#     units = ['zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight',\n",
+    "#             'nine', 'ten', 'eleven', 'twelve', 'thirteen', 'fourteen', 'fifteen',\n",
+    "#             'sixteen', 'seventeen', 'eighteen', 'nineteen']\n",
+    "#     tens = ['', '', 'twenty', 'thirty', 'forty', 'fifty', 'sixty', 'seventy', 'eighty', 'ninety']\n",
+    "#     scales = ['hundred', 'thousand', 'lac','million', 'billion', 'trillion']\n",
+    "#     ordinal_words = {'first':1, 'second':2, 'third':3, 'fifth':5, 'eighth':8, 'ninth':9, 'twelfth':12}\n",
+    "#     ordinal_endings = [('ieth', 'y'), ('th', '')]\n",
+    "\n",
+    "#     if not numwords:\n",
+    "#         numwords['and'] = (1, 0)\n",
+    "#         for idx, word in enumerate(units): numwords[word] = (1, idx)\n",
+    "#         for idx, word in enumerate(tens): numwords[word] = (1, idx * 10)\n",
+    "#         for idx, word in enumerate(scales): numwords[word] = (10 ** (idx * 3 or 2), 0)\n",
+    "\n",
+    "#     textnum = textnum.replace('-', ' ')\n",
+    "\n",
+    "#     current = result = 0\n",
+    "#     curstring = ''\n",
+    "#     onnumber = False\n",
+    "#     lastunit = False\n",
+    "#     lastscale = False\n",
+    "\n",
+    "#     def is_numword(x):\n",
+    "#         if is_number(x):\n",
+    "#             return True\n",
+    "#         if word in numwords:\n",
+    "#             return True\n",
+    "#         return False\n",
+    "\n",
+    "#     def from_numword(x):\n",
+    "#         if is_number(x):\n",
+    "#             scale = 0\n",
+    "#             increment = int(x.replace(',', ''))\n",
+    "#             return scale, increment\n",
+    "#         return numwords[x]\n",
+    "\n",
+    "#     for word in textnum.split():\n",
+    "#         if word in ordinal_words:\n",
+    "#             scale, increment = (1, ordinal_words[word])\n",
+    "#             current = current * scale + increment\n",
+    "#             if scale > 100:\n",
+    "#                 result += current\n",
+    "#                 current = 0\n",
+    "#             onnumber = True\n",
+    "#             lastunit = False\n",
+    "#             lastscale = False\n",
+    "#         else:\n",
+    "#             for ending, replacement in ordinal_endings:\n",
+    "#                 if word.endswith(ending):\n",
+    "#                     word = \"%s%s\" % (word[:-len(ending)], replacement)\n",
+    "\n",
+    "#             if (not is_numword(word)) or (word == 'and' and not lastscale):\n",
+    "#                 if onnumber:\n",
+    "#                     # Flush the current number we are building\n",
+    "#                     curstring += repr(result + current) + \" \"\n",
+    "#                 curstring += word + \" \"\n",
+    "#                 result = current = 0\n",
+    "#                 onnumber = False\n",
+    "#                 lastunit = False\n",
+    "#                 lastscale = False\n",
+    "#             else:\n",
+    "#                 scale, increment = from_numword(word)\n",
+    "#                 onnumber = True\n",
+    "\n",
+    "#                 if lastunit and (word not in scales):                                                                                                                                                                                                                                         \n",
+    "#                     # Assume this is part of a string of individual numbers to                                                                                                                                                                                                                \n",
+    "#                     # be flushed, such as a zipcode \"one two three four five\"                                                                                                                                                                                                                 \n",
+    "#                     curstring += repr(result + current)                                                                                                                                                                                                                                       \n",
+    "#                     result = current = 0                                                                                                                                                                                                                                                      \n",
+    "\n",
+    "#                 if scale > 1:                                                                                                                                                                                                                                                                 \n",
+    "#                     current = max(1, current)                                                                                                                                                                                                                                                 \n",
+    "\n",
+    "#                 current = current * scale + increment                                                                                                                                                                                                                                         \n",
+    "#                 if scale > 100:                                                                                                                                                                                                                                                               \n",
+    "#                     result += current                                                                                                                                                                                                                                                         \n",
+    "#                     current = 0                                                                                                                                                                                                                                                               \n",
+    "\n",
+    "#                 lastscale = False                                                                                                                                                                                                              \n",
+    "#                 lastunit = False                                                                                                                                                \n",
+    "#                 if word in scales:                                                                                                                                                                                                             \n",
+    "#                     lastscale = True                                                                                                                                                                                                         \n",
+    "#                 elif word in units:                                                                                                                                                                                                             \n",
+    "#                     lastunit = True\n",
+    "\n",
+    "#     if onnumber:\n",
+    "#         curstring += repr(result + current)\n",
+    "\n",
+    "#     return curstring\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a87b26d7-4a0e-4fdc-b03e-1537600faf65",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from isNumber import is_number  # Remove or replace this if unnecessary\n",
+    "\n",
+    "def text_to_int(textnum, numwords={}):\n",
+    "    # Define units, tens, and scales including \"lac\"\n",
+    "    units = ['zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight',\n",
+    "            'nine', 'ten', 'eleven', 'twelve', 'thirteen', 'fourteen', 'fifteen',\n",
+    "            'sixteen', 'seventeen', 'eighteen', 'nineteen']\n",
+    "    tens = ['', '', 'twenty', 'thirty', 'forty', 'fifty', 'sixty', 'seventy', 'eighty', 'ninety']\n",
+    "    scales = ['hundred', 'thousand', 'lac', 'million', 'billion', 'trillion']  # \"lac\" added\n",
+    "    ordinal_words = {'first': 1, 'second': 2, 'third': 3, 'fifth': 5, 'eighth': 8, 'ninth': 9, 'twelfth': 12}\n",
+    "    ordinal_endings = [('ieth', 'y'), ('th', '')]\n",
+    "\n",
+    "    if not numwords:\n",
+    "        numwords['and'] = (1, 0)  # Handle \"one hundred and twenty\"\n",
+    "        \n",
+    "        # Add units, tens, and scales to numwords\n",
+    "        for idx, word in enumerate(units):\n",
+    "            numwords[word] = (1, idx)\n",
+    "        for idx, word in enumerate(tens):\n",
+    "            numwords[word] = (1, idx * 10)\n",
+    "        \n",
+    "        for idx, word in enumerate(scales):\n",
+    "            numwords[word] = (10 ** (5 if word == 'lac' else idx * 3 or 2), 0)  # Handle \"lac\" as 10^5\n",
+    "\n",
+    "    # Remove hyphens and normalize input\n",
+    "    textnum = textnum.replace('-', ' ')\n",
+    "\n",
+    "    current = result = 0\n",
+    "    curstring = ''\n",
+    "    onnumber = False\n",
+    "    lastunit = False\n",
+    "    lastscale = False\n",
+    "\n",
+    "    def is_numword(x):\n",
+    "        return is_number(x) or x in numwords\n",
+    "\n",
+    "    def from_numword(x):\n",
+    "        if is_number(x):\n",
+    "            return 0, int(x.replace(',', ''))\n",
+    "        return numwords[x]\n",
+    "\n",
+    "    for word in textnum.split():\n",
+    "        if word in ordinal_words:\n",
+    "            scale, increment = (1, ordinal_words[word])\n",
+    "            current = current * scale + increment\n",
+    "            if scale > 100:\n",
+    "                result += current\n",
+    "                current = 0\n",
+    "            onnumber = True\n",
+    "            lastunit = False\n",
+    "            lastscale = False\n",
+    "        else:\n",
+    "            for ending, replacement in ordinal_endings:\n",
+    "                if word.endswith(ending):\n",
+    "                    word = f\"{word[:-len(ending)]}{replacement}\"\n",
+    "\n",
+    "            if not is_numword(word) or (word == 'and' and not lastscale):\n",
+    "                if onnumber:\n",
+    "                    curstring += repr(result + current) + \" \"\n",
+    "                curstring += word + \" \"\n",
+    "                result = current = 0\n",
+    "                onnumber = False\n",
+    "                lastunit = False\n",
+    "                lastscale = False\n",
+    "            else:\n",
+    "                scale, increment = from_numword(word)\n",
+    "                onnumber = True\n",
+    "\n",
+    "                if lastunit and word not in scales:\n",
+    "                    curstring += repr(result + current) + \" \"\n",
+    "                    result = current = 0\n",
+    "\n",
+    "                if scale > 1:\n",
+    "                    current = max(1, current)\n",
+    "\n",
+    "                current = current * scale + increment\n",
+    "\n",
+    "                if scale >= 100:\n",
+    "                    result += current\n",
+    "                    current = 0\n",
+    "\n",
+    "                lastscale = word in scales\n",
+    "                lastunit = word in units\n",
+    "\n",
+    "    if onnumber:\n",
+    "        curstring += repr(result + current)\n",
+    "\n",
+    "    return curstring.strip()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "83997c73-e1b4-4863-b1df-d6de6153e80d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}