update CheckSpec notebook

notebooks/dataset_analysis/CheckSpectrograms.ipynb

@@ -2,9 +2,11 @@
  "cells": [
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "Collapsed": "false"
    },
+   "outputs": [],
    "source": [
     "%matplotlib inline\n",
     "\n",
@@ -14,18 +16,18 @@
     "\n",
     "import IPython.display as ipd\n",
     "import glob"
-   ],
+   ]
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "Collapsed": "false"
    },
+   "outputs": [],
    "source": [
-    "config_path = \"/home/erogol/Projects/TTS/tts/tts/config_thorsten_de.json\"\n",
+    "config_path = \"/home/erogol/gdrive/Projects/TTS/recipes/ljspeech/align_tts/config_transformer2.json\"\n",
-    "data_path = \"/home/erogol/Data/thorsten-german/\"\n",
+    "data_path = \"/home/erogol/gdrive/Datasets/LJSpeech-1.1/\"\n",
     "\n",
     "file_paths = glob.glob(data_path + \"/**/*.wav\", recursive=True)\n",
     "CONFIG = load_config(config_path)\n",
@@ -37,9 +39,7 @@
     "\n",
     "print(\"File list, by index:\")\n",
     "dict(enumerate(file_paths))"
-   ],
+   ]
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -56,9 +56,11 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "Collapsed": "false"
    },
+   "outputs": [],
    "source": [
     "tune_params={\n",
     "#  'audio_processor': 'audio',\n",
@@ -80,7 +82,7 @@
     "# These options have to be forced off in order to avoid errors about the \n",
     "# pre-calculated not matching the options being tuned.\n",
     "reset={\n",
-    " 'signal_norm': False,\n",
+    " 'signal_norm': True,  # check this if you want to test normalization parameters.\n",
     " 'stats_path': None,\n",
     " 'symmetric_norm': False,\n",
     " 'max_norm': 1,\n",
@@ -93,9 +95,7 @@
     "tuned_config.update(tune_params)\n",
     "\n",
     "AP = AudioProcessor(**tuned_config);"
-   ],
+   ]
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -108,15 +108,15 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "Collapsed": "false"
    },
+   "outputs": [],
    "source": [
     "wav = AP.load_wav(SAMPLE_FILE_PATH)\n",
     "ipd.Audio(data=wav, rate=AP.sample_rate) "
-   ],
+   ]
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -129,29 +129,30 @@
   },
   {
    "cell_type": "code",
-   "source": [
-    "AP.power = 1.0"
-   ],
    "execution_count": null,
-   "outputs": []
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "AP.power = 1.5"
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "Collapsed": "false"
    },
+   "outputs": [],
    "source": [
     "mel = AP.melspectrogram(wav)\n",
     "print(\"Max:\", mel.max())\n",
     "print(\"Min:\", mel.min())\n",
     "print(\"Mean:\", mel.mean())\n",
-    "plot_spectrogram(mel.T, AP);\n",
+    "plot_spectrogram(mel.T, AP, output_fig=True)\n",
     "\n",
     "wav_gen = AP.inv_melspectrogram(mel)\n",
     "ipd.Audio(wav_gen, rate=AP.sample_rate)"
-   ],
+   ]
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -164,21 +165,21 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "Collapsed": "false"
    },
+   "outputs": [],
    "source": [
     "spec = AP.spectrogram(wav)\n",
     "print(\"Max:\", spec.max())\n",
     "print(\"Min:\", spec.min())\n",
     "print(\"Mean:\", spec.mean())\n",
-    "plot_spectrogram(spec.T, AP);\n",
+    "plot_spectrogram(spec.T, AP, output_fig=True)\n",
     "\n",
     "wav_gen = AP.inv_spectrogram(spec)\n",
     "ipd.Audio(wav_gen, rate=AP.sample_rate)"
-   ],
+   ]
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -193,9 +194,11 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "Collapsed": "false"
    },
+   "outputs": [],
    "source": [
     "from librosa import display\n",
     "from matplotlib import pylab as plt\n",
@@ -235,31 +238,29 @@
     "        val = values[idx]\n",
     "        print(\" > {} = {}\".format(attribute, val))\n",
     "        IPython.display.display(IPython.display.Audio(wav_gen, rate=AP.sample_rate))"
-   ],
+   ]
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "Collapsed": "false"
    },
+   "outputs": [],
    "source": [
     "compare_values(\"preemphasis\", [0, 0.5, 0.97, 0.98, 0.99])"
-   ],
+   ]
-   "execution_count": null,
-   "outputs": []
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
     "Collapsed": "false"
    },
+   "outputs": [],
    "source": [
-    "compare_values(\"ref_level_db\", [2, 5, 10, 15, 20, 25, 30, 35, 40, 100])"
+    "compare_values(\"ref_level_db\", [2, 5, 10, 15, 20, 25, 30, 35, 40, 1000])"
-   ],
+   ]
-   "execution_count": null,
-   "outputs": []
   }
  ],
  "metadata": {