coqui-tts/notebooks/TacotronPlayGround.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "import os\n",
    "import sys\n",
    "import io\n",
    "import torch \n",
    "import time\n",
    "import numpy as np\n",
    "from collections import OrderedDict\n",
    "\n",
    "%pylab inline\n",
    "rcParams[\"figure.figsize\"] = (16,5)\n",
    "sys.path.append('/home/erogol/projects/')\n",
    "\n",
    "import librosa\n",
    "import librosa.display\n",
    "\n",
    "from torchviz import make_dot, make_dot_from_trace\n",
    "\n",
    "from TTS.models.tacotron import Tacotron \n",
    "from TTS.layers import *\n",
    "from TTS.utils.data import *\n",
    "from TTS.utils.audio import AudioProcessor\n",
    "from TTS.utils.generic_utils import load_config\n",
    "from TTS.utils.text import text_to_sequence\n",
    "\n",
    "import IPython\n",
    "from IPython.display import Audio\n",
    "from utils import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def tts(model, text, CONFIG, use_cuda, ap, figures=True):\n",
    "    t_1 = time.time()\n",
    "    waveform, alignment, spectrogram = create_speech(model, text, CONFIG, use_cuda, ap) \n",
    "    print(\" >  Run-time: {}\".format(time.time() - t_1))\n",
    "    if figures:                                                                                                         \n",
    "        visualize(alignment, spectrogram, CONFIG)                                                                       \n",
    "    IPython.display.display(Audio(waveform, rate=CONFIG.sample_rate))  \n",
    "    return alignment, spectrogram"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Set constants\n",
    "ROOT_PATH = '/data/shared/erogol_models/March-28-2018_06:24PM/'\n",
    "MODEL_PATH = ROOT_PATH + '/best_model.pth.tar'\n",
    "CONFIG_PATH = ROOT_PATH + '/config.json'\n",
    "OUT_FOLDER = ROOT_PATH + '/test/'\n",
    "CONFIG = load_config(CONFIG_PATH)\n",
    "use_cuda = False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# load the model\n",
    "model = Tacotron(CONFIG.embedding_size, CONFIG.num_mels, CONFIG.num_freq, CONFIG.r)\n",
    "\n",
    "# load the audio processor\n",
    "ap = AudioProcessor(CONFIG.sample_rate, CONFIG.num_mels, CONFIG.min_level_db,\n",
    "                    CONFIG.frame_shift_ms, CONFIG.frame_length_ms, CONFIG.preemphasis,\n",
    "                    CONFIG.ref_level_db, CONFIG.num_freq, CONFIG.power, griffin_lim_iters=80)         \n",
    "\n",
    "\n",
    "# load model state\n",
    "if use_cuda:\n",
    "    cp = torch.load(MODEL_PATH)\n",
    "else:\n",
    "    cp = torch.load(MODEL_PATH, map_location=lambda storage, loc: storage)\n",
    "\n",
    "# # small trick to remove DataParallel wrapper\n",
    "new_state_dict = OrderedDict()\n",
    "for k, v in cp['model'].items():\n",
    "    name = k[7:] # remove `module.`\n",
    "    new_state_dict[name] = v\n",
    "cp['model'] = new_state_dict\n",
    "\n",
    "# load the model\n",
    "model.load_state_dict(cp['model'])\n",
    "if use_cuda:\n",
    "    model.cuda()\n",
    "model.eval()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### EXAMPLES FROM TRAINING SET"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "df = pd.read_csv('/data/shared/KeithIto/LJSpeech-1.0/metadata.csv', delimiter='|')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "sentence = df.iloc[120, 1].lower().replace(',','')\n",
    "print(sentence)\n",
    "align = tts(model, sentence, CONFIG, use_cuda, ap)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### NEW EXAMPLES"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "sentence =  \"Will Donald Trump Jr. offer the country’s business leaders a peek into a new U.S.-India relationship in trade? Defense? Terrorism?\"\n",
    "model.decoder.max_decoder_steps = 300\n",
    "alignment = tts(model, sentence, CONFIG, use_cuda, ap)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}