{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "64d773c6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    }
   ],
   "source": [
    "%pylab inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "fe6f477a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "os.environ['CUDA_VISIBLE_DEVICES'] = ''"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0d497284",
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import tempfile\n",
    "\n",
    "from multiprocessing import Pool\n",
    "import tqdm\n",
    "\n",
    "from suno_utils.utils.text import normalize_whitespace"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "03c83647",
   "metadata": {},
   "outputs": [],
   "source": [
    "DATA_DIR = \"/mnt/data-ssd-1/data/europarl/\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "b28ab272",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ep-asr.lm.test.spk-dep.tr.en.csv\r\n",
      "ep-asr.lm.test.spk-dep.tr.en.orig.txt.gz\r\n",
      "ep-asr.lm.test.spk-dep.tr.en.rev.txt.gz\r\n",
      "ep-asr.lm.test.spk-indep.tr.en.csv\r\n",
      "ep-asr.lm.test.spk-indep.tr.en.orig.txt.gz\r\n",
      "ep-asr.lm.test.spk-indep.tr.en.rev.txt.gz\r\n"
     ]
    }
   ],
   "source": [
    "!ls /mnt/data-ssd-1/data/europarl/release/en/test/text/raw"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "9806d13a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "test.spk-dep.rev.lines.prepro.txt.gz  test.spk-indep.rev.lines.prepro.txt.gz\r\n"
     ]
    }
   ],
   "source": [
    "!ls /mnt/data-ssd-1/data/europarl/release/en/test/text/prepro"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "48eaa389",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "speakers_speeches  speeches.csv\r\n"
     ]
    }
   ],
   "source": [
    "!ls /mnt/data-ssd-1/data/europarl/release/en/test/original_audio/spk-dep/lists"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "0ee313b8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "speakers.csv\t      speakers.json  speeches.headers.csv\r\n",
      "speakers.headers.csv  speeches.csv   speeches.json\r\n"
     ]
    }
   ],
   "source": [
    "!ls /mnt/data-ssd-1/data/europarl/release/en/test/original_audio/spk-dep/metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "5ba19bd1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ep-asr.en.test.spk-dep.orig.ref  ep-asr.en.test.spk-dep.rev.ref\r\n",
      "ep-asr.en.test.spk-dep.orig.stm  ep-asr.en.test.spk-dep.rev.stm\r\n"
     ]
    }
   ],
   "source": [
    "!ls /mnt/data-ssd-1/data/europarl/release/en/test/original_audio/spk-dep/refs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "b85407a1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "t8  t9\r\n"
     ]
    }
   ],
   "source": [
    "!ls /mnt/data-ssd-1/data/europarl/release/en/test/original_audio/spk-dep/speeches"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ecf8e01f",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5f8a7eb7",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "37fcf16f",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ebe92468",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7a34e783",
   "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": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}
