Update AnalyzeDataset notebook

notebooks/dataset_analysis/AnalyzeDataset.ipynb

@@ -8,7 +8,7 @@
    },
    "outputs": [],
    "source": [
-    "TTS_PATH = \"/home/erogol/projects/\""
+    "# TTS_PATH = \"/home/erogol/projects/\""
    ]
   },
   {
@@ -21,7 +21,6 @@
    "source": [
     "import os\n",
     "import sys\n",
-    "sys.path.append(TTS_PATH) # set this if TTS is not installed globally\n",
     "import librosa\n",
     "import numpy as np\n",
     "import pandas as pd\n",
@@ -30,6 +29,8 @@
     "from multiprocessing import Pool\n",
     "from matplotlib import pylab as plt\n",
     "from collections import Counter\n",
+    "from TTS.config.shared_configs import BaseDatasetConfig\n",
+    "from TTS.tts.datasets import load_tts_samples\n",
     "from TTS.tts.datasets.formatters import *\n",
     "%matplotlib inline"
    ]
@@ -42,22 +43,29 @@
    },
    "outputs": [],
    "source": [
-    "DATA_PATH = \"/home/erogol/Data/m-ai-labs/de_DE/by_book/male/karlsson/\"\n",
-    "META_DATA = [\"kleinzaches/metadata.csv\",\n",
-    "            \"spiegel_kaetzchen/metadata.csv\",\n",
-    "            \"herrnarnesschatz/metadata.csv\",\n",
-    "            \"maedchen_von_moorhof/metadata.csv\",\n",
-    "            \"koenigsgaukler/metadata.csv\",\n",
-    "            \"altehous/metadata.csv\",\n",
-    "            \"odysseus/metadata.csv\",\n",
-    "            \"undine/metadata.csv\",\n",
-    "            \"reise_tilsit/metadata.csv\",\n",
-    "            \"schmied_seines_glueckes/metadata.csv\",\n",
-    "            \"kammmacher/metadata.csv\",\n",
-    "            \"unterm_birnbaum/metadata.csv\",\n",
-    "            \"liebesbriefe/metadata.csv\",\n",
-    "            \"sandmann/metadata.csv\"]\n",
-    "NUM_PROC = 8"
+    "NUM_PROC = 8\n",
+    "DATASET_CONFIG = BaseDatasetConfig(\n",
+    "    name=\"ljspeech\", meta_file_train=\"metadata.csv\", path=\"/home/ubuntu/TTS/depot/data/male_dataset1_44k/\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def formatter(root_path, meta_file, **kwargs):  # pylint: disable=unused-argument\n",
+    "    txt_file = os.path.join(root_path, meta_file)\n",
+    "    items = []\n",
+    "    speaker_name = \"maledataset1\"\n",
+    "    with open(txt_file, \"r\", encoding=\"utf-8\") as ttf:\n",
+    "        for line in ttf:\n",
+    "            cols = line.split(\"|\")\n",
+    "            wav_file = os.path.join(root_path, \"wavs\", cols[0])\n",
+    "            text = cols[1]\n",
+    "            items.append([text, wav_file, speaker_name])\n",
+    "    return items"
    ]
   },
   {
@@ -69,8 +77,10 @@
    "outputs": [],
    "source": [
     "# use your own preprocessor at this stage - TTS/datasets/proprocess.py\n",
-    "items = mailabs(DATA_PATH, META_DATA)\n",
-    "print(\" > Number of audio files: {}\".format(len(items)))"
+    "train_samples, eval_samples = load_tts_samples(DATASET_CONFIG, eval_split=True, formatter=formatter)\n",
+    "items = train_samples + eval_samples\n",
+    "print(\" > Number of audio files: {}\".format(len(items)))\n",
+    "print(items[1])"
    ]
   },
   {
@@ -103,6 +113,15 @@
     "print([item for item, count in c.items() if count > 1])"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "item"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -112,11 +131,9 @@
    "outputs": [],
    "source": [
     "def load_item(item):\n",
-    "    file_name = item[1].strip()\n",
     "    text = item[0].strip()\n",
-    "    audio = librosa.load(file_name, sr=None)\n",
-    "    sr = audio[1]\n",
-    "    audio = audio[0]\n",
+    "    file_name = item[1].strip()\n",
+    "    audio, sr = librosa.load(file_name, sr=None)\n",
     "    audio_len = len(audio) / sr\n",
     "    text_len = len(text)\n",
     "    return file_name, text, text_len, audio, audio_len\n",
@@ -374,11 +391,18 @@
     "# fequency bar plot - it takes time!!\n",
     "w_count_df.plot.bar()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -392,7 +416,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,