TTS/notebooks/dataset_analysis/CheckPitch.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ],
   "outputs": [],
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "source": [
    "import numpy as np\n",
    "import glob\n",
    "from TTS.utils.audio import AudioProcessor\n",
    "from TTS.config.shared_configs import BaseAudioConfig\n",
    "from TTS.tts.utils.visual import plot_pitch"
   ],
   "outputs": [],
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "source": [
    "pitch_path = \"/home/ubuntu/TTS/recipes/ljspeech/fast_pitch/f0_cache\"\n",
    "wav_path = \"/home/ubuntu/TTS/recipes/ljspeech/LJSpeech-1.1/wavs\"\n",
    "wav_files = glob.glob(\"/home/ubuntu/TTS/recipes/ljspeech/LJSpeech-1.1/wavs/*.wav\")\n",
    "print(len(wav_files))"
   ],
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "13100\n"
     ]
    }
   ],
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "source": [
    "ap = AudioProcessor(**BaseAudioConfig( sample_rate=22050,\n",
    "    do_trim_silence=True,\n",
    "    trim_db=60.0,\n",
    "    signal_norm=False,\n",
    "    mel_fmin=0.0,\n",
    "    mel_fmax=8000,\n",
    "    spec_gain=1.0,\n",
    "    log_func=\"np.log\",\n",
    "    ref_level_db=20,\n",
    "    preemphasis=0.0,))"
   ],
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      " > Setting up Audio Processor...\n",
      " | > sample_rate:22050\n",
      " | > resample:False\n",
      " | > num_mels:80\n",
      " | > log_func:np.log\n",
      " | > min_level_db:-100\n",
      " | > frame_shift_ms:None\n",
      " | > frame_length_ms:None\n",
      " | > ref_level_db:20\n",
      " | > fft_size:1024\n",
      " | > power:1.5\n",
      " | > preemphasis:0.0\n",
      " | > griffin_lim_iters:60\n",
      " | > signal_norm:False\n",
      " | > symmetric_norm:True\n",
      " | > mel_fmin:0\n",
      " | > mel_fmax:8000\n",
      " | > spec_gain:1.0\n",
      " | > stft_pad_mode:reflect\n",
      " | > max_norm:4.0\n",
      " | > clip_norm:True\n",
      " | > do_trim_silence:True\n",
      " | > trim_db:60.0\n",
      " | > do_sound_norm:False\n",
      " | > do_amp_to_db_linear:True\n",
      " | > do_amp_to_db_mel:True\n",
      " | > stats_path:None\n",
      " | > base:2.718281828459045\n",
      " | > hop_length:256\n",
      " | > win_length:1024\n"
     ]
    }
   ],
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "source": [
    "pitch_files = [wf.replace(\".wav\", \"_pitch.npy\").replace(wav_path, pitch_path) for wf in wav_files]"
   ],
   "outputs": [],
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "source": [
    "idx = 100\n",
    "# wav_file = wav_files[idx]\n",
    "# pitch_file = pitch_files[idx]\n",
    "wav_file = \"/home/ubuntu/TTS/recipes/ljspeech/fast_pitch/../LJSpeech-1.1/wavs/LJ011-0097.wav\"\n",
    "pitch_file = \"/home/ubuntu/TTS/recipes/ljspeech/fast_pitch/f0_cache/LJ011-0097_pitch.npy\"\n",
    "pitch = np.load(pitch_file)\n",
    "wav = ap.load_wav(wav_file)\n",
    "spec = ap.melspectrogram(wav)"
   ],
   "outputs": [],
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "source": [
    "plot_pitch(pitch, spec.T)"
   ],
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 2160x720 with 2 Axes>"
      ]
     },
     "metadata": {},
     "execution_count": 31
    }
   ],
   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "source": [],
   "outputs": [],
   "metadata": {}
  }
 ],
 "metadata": {
  "orig_nbformat": 4,
  "language_info": {
   "name": "python",
   "version": "3.9.7",
   "mimetype": "text/x-python",
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "pygments_lexer": "ipython3",
   "nbconvert_exporter": "python",
   "file_extension": ".py"
  },
  "kernelspec": {
   "name": "python3",
   "display_name": "Python 3.9.1 64-bit ('miniconda3': virtualenv)"
  },
  "interpreter": {
   "hash": "822ce188d9bce5372c4adbb11364eeb49293228c2224eb55307f4664778e7f56"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}