Delete Tamil_number_conversion.ipynb

Tamil_number_conversion.ipynb

@@ -1,223 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "dc09394e-2130-4bd4-af30-01346d8ee355",
-   "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"
-     ]
-    },
-    {
-     "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": 1,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\gradio\\analytics.py:106: UserWarning: IMPORTANT: You are using gradio version 4.37.2, however version 4.44.1 is available, please upgrade. \n",
-      "--------\n",
-      "  warnings.warn(\n",
-      "ERROR:    Exception in ASGI application\n",
-      "Traceback (most recent call last):\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\uvicorn\\protocols\\http\\h11_impl.py\", line 404, in run_asgi\n",
-      "    result = await app(  # type: ignore[func-returns-value]\n",
-      "             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\uvicorn\\middleware\\proxy_headers.py\", line 84, in __call__\n",
-      "    return await self.app(scope, receive, send)\n",
-      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\fastapi\\applications.py\", line 1054, in __call__\n",
-      "    await super().__call__(scope, receive, send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\applications.py\", line 123, in __call__\n",
-      "    await self.middleware_stack(scope, receive, send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\middleware\\errors.py\", line 186, in __call__\n",
-      "    raise exc\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\middleware\\errors.py\", line 164, in __call__\n",
-      "    await self.app(scope, receive, _send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\gradio\\route_utils.py\", line 714, in __call__\n",
-      "    await self.app(scope, receive, send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\middleware\\exceptions.py\", line 62, in __call__\n",
-      "    await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\_exception_handler.py\", line 64, in wrapped_app\n",
-      "    raise exc\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\_exception_handler.py\", line 53, in wrapped_app\n",
-      "    await app(scope, receive, sender)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\routing.py\", line 762, in __call__\n",
-      "    await self.middleware_stack(scope, receive, send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\routing.py\", line 782, in app\n",
-      "    await route.handle(scope, receive, send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\routing.py\", line 297, in handle\n",
-      "    await self.app(scope, receive, send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\routing.py\", line 77, in app\n",
-      "    await wrap_app_handling_exceptions(app, request)(scope, receive, send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\_exception_handler.py\", line 64, in wrapped_app\n",
-      "    raise exc\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\_exception_handler.py\", line 53, in wrapped_app\n",
-      "    await app(scope, receive, sender)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\routing.py\", line 75, in app\n",
-      "    await response(scope, receive, send)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\responses.py\", line 346, in __call__\n",
-      "    await send(\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\_exception_handler.py\", line 50, in sender\n",
-      "    await send(message)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\_exception_handler.py\", line 50, in sender\n",
-      "    await send(message)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\starlette\\middleware\\errors.py\", line 161, in _send\n",
-      "    await send(message)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\uvicorn\\protocols\\http\\h11_impl.py\", line 508, in send\n",
-      "    output = self.conn.send(event=h11.EndOfMessage())\n",
-      "             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\h11\\_connection.py\", line 512, in send\n",
-      "    data_list = self.send_with_data_passthrough(event)\n",
-      "                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\h11\\_connection.py\", line 545, in send_with_data_passthrough\n",
-      "    writer(event, data_list.append)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\h11\\_writers.py\", line 67, in __call__\n",
-      "    self.send_eom(event.headers, write)\n",
-      "  File \"C:\\Users\\WCHL\\anaconda3\\envs\\RunInference2\\Lib\\site-packages\\h11\\_writers.py\", line 96, in send_eom\n",
-      "    raise LocalProtocolError(\"Too little data for declared Content-Length\")\n",
-      "h11._util.LocalProtocolError: Too little data for declared Content-Length\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "எண்பது\n",
-      "எண்பது\n",
-      "எண்பது\n",
-      "eighty\n",
-      "80\n"
-     ]
-    }
-   ],
-   "source": [
-    "import gradio as gr\n",
-    "import librosa\n",
-    "import numpy as np\n",
-    "import pywt\n",
-    "import nbimporter\n",
-    "from scipy.signal import butter, lfilter, wiener\n",
-    "from scipy.io.wavfile import write\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",
-    "\n",
-    "asr_model = pipeline(\"automatic-speech-recognition\", model=\"cdactvm/w2v-bert-tamil_new\")\n",
-    "\n",
-    "# Function to apply a high-pass filter\n",
-    "def high_pass_filter(audio, sr, cutoff=300):\n",
-    "    nyquist = 0.5 * sr\n",
-    "    normal_cutoff = cutoff / nyquist\n",
-    "    b, a = butter(1, normal_cutoff, btype='high', analog=False)\n",
-    "    filtered_audio = lfilter(b, a, audio)\n",
-    "    return filtered_audio\n",
-    "\n",
-    "# Function to apply wavelet denoising\n",
-    "def wavelet_denoise(audio, wavelet='db1', level=1):\n",
-    "    coeffs = pywt.wavedec(audio, wavelet, mode='per')\n",
-    "    sigma = np.median(np.abs(coeffs[-level])) / 0.5\n",
-    "    uthresh = sigma * np.sqrt(2 * np.log(len(audio)))\n",
-    "    coeffs[1:] = [pywt.threshold(i, value=uthresh, mode='soft') for i in coeffs[1:]]\n",
-    "    return pywt.waverec(coeffs, wavelet, mode='per')\n",
-    "\n",
-    "# Function to apply a Wiener filter for noise reduction\n",
-    "def apply_wiener_filter(audio):\n",
-    "    return wiener(audio)\n",
-    "\n",
-    "# Function to handle speech recognition\n",
-    "def recognize_speech(audio_file):\n",
-    "    audio, sr = librosa.load(audio_file, sr=16000)\n",
-    "    audio = high_pass_filter(audio, sr)\n",
-    "    audio = apply_wiener_filter(audio)\n",
-    "    denoised_audio = wavelet_denoise(audio)\n",
-    "    result = asr_model(denoised_audio)\n",
-    "    text_value = result['text']\n",
-    "    cleaned_text = text_value.replace(\"<s>\", \"\")\n",
-    "    print(cleaned_text)\n",
-    "    converted_to_list = convert_to_list(cleaned_text, text_to_list())\n",
-    "    print(converted_to_list)\n",
-    "    processed_doubles = process_doubles(converted_to_list)\n",
-    "    print(processed_doubles)\n",
-    "    replaced_words = replace_words(processed_doubles)\n",
-    "    print(replaced_words)\n",
-    "    converted_text = text_to_int(replaced_words)\n",
-    "    print(converted_text)\n",
-    "    return converted_text\n",
-    "\n",
-    "# Gradio Interface\n",
-    "gr.Interface(\n",
-    "    fn=recognize_speech,\n",
-    "    inputs=gr.Audio(sources=[\"microphone\",\"upload\"], type=\"filepath\"),\n",
-    "    outputs=\"text\",\n",
-    "    title=\"Speech Recognition with Advanced Noise Reduction & Hindi ASR\",\n",
-    "    description=\"Upload an audio file, and the system will use high-pass filtering, Wiener filtering, and wavelet-based denoising, then a Hindi ASR model will transcribe the clean audio.\"\n",
-    ").launch()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "d4565cfb-a8e0-49a1-8878-6e5b1cd105e6",
-   "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
-}