{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Local Transcribe with Whisper\n",
    "## Example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Help on function transcribe in module src._LocalTranscribe:\n",
      "\n",
      "transcribe(path, glob_file, model=None, language=None, verbose=False)\n",
      "    Transcribes audio files in a specified folder using OpenAI's Whisper model.\n",
      "    \n",
      "    Args:\n",
      "        path (str): Path to the folder containing the audio files.\n",
      "        glob_file (list): List of audio file paths to transcribe.\n",
      "        model (str, optional): Name of the Whisper model to use for transcription.\n",
      "            Defaults to None, which uses the default model.\n",
      "        language (str, optional): Language code for transcription. Defaults to None,\n",
      "            which enables automatic language detection.\n",
      "        verbose (bool, optional): If True, enables verbose mode with detailed information\n",
      "            during the transcription process. Defaults to False.\n",
      "    \n",
      "    Returns:\n",
      "        str: A message indicating the result of the transcription process.\n",
      "    \n",
      "    Raises:\n",
      "        RuntimeError: If an invalid file is encountered, it will be skipped.\n",
      "    \n",
      "    Notes:\n",
      "        - The function downloads the specified model if not available locally.\n",
      "        - The transcribed text files will be saved in a \"transcriptions\" folder\n",
      "          within the specified path.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Import the modules and get the docstring\n",
    "from src._LocalTranscribe import transcribe, get_path\n",
    "help(transcribe)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set the variables\n",
    "path='sample_audio/'# Folder path\n",
    "model='small' # Model size\n",
    "language= None # Preset language, None for automatic detection\n",
    "verbose = True # Output transcription in realtime\n",
    "\n",
    "# Get glob file, additional step for app version.\n",
    "\n",
    "glob_file = get_path(path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Trying to transcribe file named: Armstrong_Small_Step🕐\n",
      "Detecting language using up to the first 30 seconds. Use `--language` to specify the language\n",
      "Detected language: English\n",
      "[00:00.000 --> 00:07.000]  I'm going to step off the limb now.\n",
      "[00:07.000 --> 00:18.000]  That's one small step for man.\n",
      "[00:18.000 --> 00:24.000]  One giant leap for mankind.\n",
      "\n",
      "Trying to transcribe file named: Axel_Pettersson_röstinspelning🕐\n",
      "Detecting language using up to the first 30 seconds. Use `--language` to specify the language\n",
      "Detected language: Swedish\n",
      "[00:00.000 --> 00:06.140]  Hej, jag heter Axel Pettersson. Jag följer bror 1976.\n",
      "[00:06.400 --> 00:15.100]  Jag har varit vikerpedjan sen 2008 och jag har översatt röstintroduktionsprojektet till svenska.\n",
      "\n",
      "Trying to transcribe file named: readme🕐\n",
      "Not a valid file, skipping.\n",
      "\n",
      "Trying to transcribe file named: transcriptions🕐\n",
      "Not a valid file, skipping.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Finished transcription, 2 files can be found in sample_audio//transcriptions'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Run the script\n",
    "transcribe(path, glob_file, model, language, verbose)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "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": "3.10.4"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}