ParakeetRebeccaRosario/examples/tacotron2_aishell3/voice_cloning.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import paddle\n",
    "from matplotlib import pyplot as plt\n",
    "from IPython import display as ipd\n",
    "import soundfile as sf\n",
    "import librosa.display\n",
    "from parakeet.utils import display\n",
    "paddle.set_device(\"gpu:0\")\n",
    "import sys\n",
    "sys.path.append(\"../../\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 加载模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "vocab_phones:\n",
      " Vocab(size: 68,\n",
      "stoi:\n",
      "OrderedDict([('<pad>', 0), ('<unk>', 1), ('<s>', 2), ('</s>', 3), ('$', 4), ('%', 5), ('&r', 6), ('a', 7), ('ai', 8), ('an', 9), ('ang', 10), ('ao', 11), ('b', 12), ('c', 13), ('ch', 14), ('d', 15), ('e', 16), ('ea', 17), ('ei', 18), ('en', 19), ('eng', 20), ('er', 21), ('f', 22), ('g', 23), ('h', 24), ('i', 25), ('ia', 26), ('iai', 27), ('ian', 28), ('iang', 29), ('iao', 30), ('ie', 31), ('ien', 32), ('ieng', 33), ('ii', 34), ('iii', 35), ('io', 36), ('iou', 37), ('j', 38), ('k', 39), ('l', 40), ('m', 41), ('n', 42), ('o', 43), ('ou', 44), ('p', 45), ('q', 46), ('r', 47), ('s', 48), ('sh', 49), ('t', 50), ('u', 51), ('ua', 52), ('uai', 53), ('uan', 54), ('uang', 55), ('uei', 56), ('uen', 57), ('ueng', 58), ('uo', 59), ('v', 60), ('van', 61), ('ve', 62), ('ven', 63), ('veng', 64), ('x', 65), ('z', 66), ('zh', 67)]))\n",
      "vocab+tones:\n",
      " Vocab(size: 10,\n",
      "stoi:\n",
      "OrderedDict([('<pad>', 0), ('<unk>', 1), ('<s>', 2), ('</s>', 3), ('0', 4), ('1', 5), ('2', 6), ('3', 7), ('4', 8), ('5', 9)]))\n"
     ]
    }
   ],
   "source": [
    "from examples.ge2e.audio_processor import SpeakerVerificationPreprocessor\n",
    "from parakeet.models.lstm_speaker_encoder import LSTMSpeakerEncoder\n",
    "\n",
    "# speaker encoder\n",
    "p = SpeakerVerificationPreprocessor(\n",
    "    sampling_rate=16000, \n",
    "    audio_norm_target_dBFS=-30, \n",
    "    vad_window_length=30, \n",
    "    vad_moving_average_width=8, \n",
    "    vad_max_silence_length=6, \n",
    "    mel_window_length=25, \n",
    "    mel_window_step=10, \n",
    "    n_mels=40, \n",
    "    partial_n_frames=160, \n",
    "    min_pad_coverage=0.75, \n",
    "    partial_overlap_ratio=0.5)\n",
    "speaker_encoder = LSTMSpeakerEncoder(n_mels=40, num_layers=3, hidden_size=256, output_size=256)\n",
    "speaker_encoder_params_path = \"../../pretrained/ge2e/ge2e_ckpt_0.3/step-3000000.pdparams\"\n",
    "speaker_encoder.set_state_dict(paddle.load(speaker_encoder_params_path))\n",
    "speaker_encoder.eval()\n",
    "\n",
    "# synthesizer\n",
    "from parakeet.models.tacotron2 import Tacotron2\n",
    "from examples.tacotron2_aishell3.chinese_g2p import convert_sentence\n",
    "from examples.tacotron2_aishell3.aishell3 import voc_phones, voc_tones\n",
    "\n",
    "synthesizer = Tacotron2(\n",
    "    vocab_size=68,\n",
    "    n_tones=10,\n",
    "    d_mels= 80,\n",
    "    d_encoder= 512,\n",
    "    encoder_conv_layers = 3,\n",
    "    encoder_kernel_size= 5,\n",
    "    d_prenet= 256,\n",
    "    d_attention_rnn= 1024,\n",
    "    d_decoder_rnn = 1024,\n",
    "    attention_filters = 32,\n",
    "    attention_kernel_size = 31,\n",
    "    d_attention= 128,\n",
    "    d_postnet = 512,\n",
    "    postnet_kernel_size = 5,\n",
    "    postnet_conv_layers = 5,\n",
    "    reduction_factor = 1,\n",
    "    p_encoder_dropout = 0.5,\n",
    "    p_prenet_dropout= 0.5,\n",
    "    p_attention_dropout= 0.1,\n",
    "    p_decoder_dropout= 0.1,\n",
    "    p_postnet_dropout= 0.5,\n",
    "    d_global_condition=256,\n",
    "    use_stop_token=False,\n",
    ")\n",
    "params_path = \"../../pretrained/tacotron2_aishell3/tacotron2_aishell3_ckpt_0.3/step-450000.pdparams\"\n",
    "synthesizer.set_state_dict(paddle.load(params_path))\n",
    "synthesizer.eval()\n",
    "\n",
    "# vocoder\n",
    "from parakeet.models import ConditionalWaveFlow\n",
    "vocoder = ConditionalWaveFlow(upsample_factors=[16, 16], n_flows=8, n_layers=8, n_group=16, channels=128, n_mels=80, kernel_size=[3, 3])\n",
    "params_path = \"../../pretrained/waveflow/waveflow_ljspeech_ckpt_0.3/step-2000000.pdparams\"\n",
    "vocoder.set_state_dict(paddle.load(params_path))\n",
    "vocoder.eval()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 生成 speaker encoding"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "首先在当前文件夹下新建文件夹 `ref_audio`，把要作为参考的音频存在在这个文件夹中。格式要求是 wav 格式，采样率会被重采样至 16kHz."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "                <audio  controls=\"controls\" >\n",
       "                    <source src=\"data:audio/x-wav;base64,UklGRmaYBQBXQVZFZm10IBAAAAABAAEAgLsAAAB3AQACABAATElTVDoAAABJTkZPSU5BTRcAAADnmb7luqbnp5HmioDlm60y5Y+35qW8AABJU0ZUDgAAAExhdmY1OC40NS4xMDAAZGF0YQCYBQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
       "                    Your browser does not support the audio element.\n",
       "                </audio>\n",
       "              "
      ],
      "text/plain": [
       "<IPython.lib.display.Audio object>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ref_name = \"女声2.wav\"\n",
    "ref_audio_path = f\"./ref_audio/{ref_name}\"\n",
    "ipd.Audio(ref_audio_path, normalize=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mel_sequences:  (2, 160, 40)\n",
      "embed shape:  [256]\n"
     ]
    }
   ],
   "source": [
    "mel_sequences = p.extract_mel_partials(p.preprocess_wav(ref_audio_path))\n",
    "print(\"mel_sequences: \", mel_sequences.shape)\n",
    "with paddle.no_grad():\n",
    "    embed = speaker_encoder.embed_utterance(paddle.to_tensor(mel_sequences))\n",
    "print(\"embed shape: \", embed.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 合成频谱"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "因为 AISHELL-3 数据集中使用 `%` 和 `$` 表示韵律词和韵律短语的边界，它们大约对应着较短和较长的停顿，在文本中可以使用 `%` 和 `$` 来调节韵律。\n",
    "\n",
    "值得的注意的是，句子的有效字符集仅包含汉字和 `%`, `$`, 因此输入的句子只能包含这些字符。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['m', 'ei', 'd', 'ang', 'n', 'i', 'j', 've', 'd', 'e', '%', 'x', 'iang', 'iao', 'p', 'i', 'p', 'ieng', 'sh', 'en', 'm', 'e', 'r', 'en', 'd', 'e', 'sh', 'iii', 'h', 'ou', '$', 'n', 'i', 'q', 'ie', 'iao', 'j', 'i', 'zh', 'e', '%', 'zh', 'e', 'g', 'e', 'sh', 'iii', 'j', 'ie', 'sh', 'ang', 'd', 'e', 'r', 'en', '%', 'b', 'ieng', 'f', 'ei', 'd', 'ou', 'j', 'v', 'b', 'ei', 'n', 'i', 'b', 'ieng', 'iou', 'd', 'e', 't', 'iao', 'j', 'ian', '$']\n",
      "['0', '3', '0', '1', '0', '3', '0', '2', '0', '5', '0', '0', '3', '4', '0', '1', '0', '2', '0', '2', '0', '5', '0', '2', '0', '5', '0', '2', '0', '4', '0', '0', '3', '0', '4', '4', '0', '4', '0', '5', '0', '0', '4', '0', '4', '0', '4', '0', '4', '0', '4', '0', '5', '0', '2', '0', '0', '4', '0', '1', '0', '1', '0', '4', '0', '4', '0', '3', '0', '3', '3', '0', '5', '0', '2', '0', '4', '0']\n"
     ]
    }
   ],
   "source": [
    "sentence = \"每当你觉得%想要批评什么人的时候$你切要记着%这个世界上的人%并非都具备你禀有的条件$\"\n",
    "phones, tones = convert_sentence(sentence)\n",
    "print(phones)\n",
    "print(tones)\n",
    "\n",
    "phones = np.array([voc_phones.lookup(item) for item in phones], dtype=np.int64)\n",
    "tones = np.array([voc_tones.lookup(item) for item in tones], dtype=np.int64)\n",
    "\n",
    "phones = paddle.to_tensor(phones).unsqueeze(0)\n",
    "tones = paddle.to_tensor(tones).unsqueeze(0)\n",
    "utterance_embeds = paddle.unsqueeze(embed, 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      " 74%|███████▍  | 741/1000 [00:02<00:01, 249.49it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "content exhausted!\n"
     ]
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "outputs = synthesizer.infer(phones, tones=tones, global_condition=utterance_embeds)\n",
    "mel_input = paddle.transpose(outputs[\"mel_outputs_postnet\"], [0, 2, 1])\n",
    "fig = display.plot_alignment(outputs[\"alignments\"][0].numpy().T)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 合成语音"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "合成的语音会保存在 `syn_audio` 目录下，使用和 reference 相同的文件名。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "time: 23.468628406524658s\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PolyCollection at 0x7fcd141cc650>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "with paddle.no_grad():\n",
    "    wav = vocoder.infer(mel_input)\n",
    "wav = wav.numpy()[0]\n",
    "sf.write(f\"syn_audio/{ref_name}\", wav, samplerate=22050)\n",
    "librosa.display.waveplot(wav)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "                <audio  controls=\"controls\" >\n",
       "                    <source src=\"data:audio/wav;base64,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
       "                    Your browser does not support the audio element.\n",
       "                </audio>\n",
       "              "
      ],
      "text/plain": [
       "<IPython.lib.display.Audio object>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ipd.Audio(wav, rate=22050)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}