update tts_tutorial

docs/tutorial/tts/tts_tutorial.ipynb

@@ -252,7 +252,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 25,
    "metadata": {
     "scrolled": true
    },
@@ -261,8 +261,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The autoreload extension is already loaded. To reload it, use:\n",
-      "  %reload_ext autoreload\n"
+      "env: CUDA_VISIBLE_DEVICES=0\n"
      ]
     }
    ],
@@ -284,7 +283,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 28,
    "metadata": {
     "scrolled": true
    },
@@ -317,7 +316,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 30,
    "metadata": {
     "scrolled": true
    },
@@ -596,11 +595,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 31,
    "metadata": {
     "scrolled": true
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Frontend done!\n"
+     ]
+    }
+   ],
    "source": [
     "# 传入 phones_dict 会把相应的 phones 转换成 phone_ids\n",
     "frontend = Frontend(phone_vocab_path=phones_dict)\n",
@@ -619,25 +626,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 35,
    "metadata": {
     "scrolled": true
    },
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Building prefix dict from the default dictionary ...\n",
-      "DEBUG:jieba:Building prefix dict from the default dictionary ...\n",
-      "Loading model from cache /tmp/jieba.cache\n",
-      "DEBUG:jieba:Loading model from cache /tmp/jieba.cache\n",
-      "Loading model cost 5.331 seconds.\n",
-      "DEBUG:jieba:Loading model cost 5.331 seconds.\n",
-      "Prefix dict has been built successfully.\n",
-      "DEBUG:jieba:Prefix dict has been built successfully.\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -701,8 +694,10 @@
     "<br></br>\n",
     "在本教程中，我们使用 `FastSpeech2` 作为声学模型。\n",
     "![FastSpeech2](source/fastspeech2.png)\n",
+    "\n",
     "PaddleSpeech TTS 实现的 FastSpeech2 与论文不同的地方在于，我们使用的的是 phone 级别的 `pitch` 和 `energy`(与 FastPitch 类似)。\n",
     "![FastPitch](source/fastpitch.png)\n",
+    "\n",
     "更多关于[声学模型的发展及改进](https://paddlespeech.readthedocs.io/en/latest/tts/models_introduction.html)。"
    ]
   },
@@ -1020,13 +1015,16 @@
     "odim = fastspeech2_config.n_mels\n",
     "model = FastSpeech2(\n",
     "    idim=vocab_size, odim=odim, **fastspeech2_config[\"model\"])\n",
-    "\n",
-    "model.set_state_dict(paddle.load(fastspeech2_checkpoint)[\"main_params\"]) # 加载预训练模型参数\n",
-    "model.eval() # 推理阶段不启用 batch norm 和 dropout\n",
+    "# 加载预训练模型参数\n",
+    "model.set_state_dict(paddle.load(fastspeech2_checkpoint)[\"main_params\"])\n",
+    "# 推理阶段不启用 batch norm 和 dropout\n",
+    "model.eval()\n",
     "stat = np.load(fastspeech2_stat)\n",
-    "mu, std = stat # 读取数据预处理阶段数据集的均值和标准差\n",
+    "# 读取数据预处理阶段数据集的均值和标准差\n",
+    "mu, std = stat\n",
     "mu, std = paddle.to_tensor(mu), paddle.to_tensor(std)\n",
-    "fastspeech2_normalizer = ZScore(mu, std) # 构造归一化的新模型\n",
+    "# 构造归一化的新模型\n",
+    "fastspeech2_normalizer = ZScore(mu, std)\n",
     "fastspeech2_inference = FastSpeech2Inference(fastspeech2_normalizer, model)\n",
     "fastspeech2_inference.eval()\n",
     "print(fastspeech2_inference)\n",
@@ -1153,16 +1151,18 @@
    ],
    "source": [
     "vocoder = PWGGenerator(**pwg_config[\"generator_params\"])\n",
-    "\n",
-    "vocoder.set_state_dict(paddle.load(pwg_checkpoint)[\"generator_params\"]) # 模型加载预训练参数\n",
+    "# 模型加载预训练参数\n",
+    "vocoder.set_state_dict(paddle.load(pwg_checkpoint)[\"generator_params\"]) \n",
     "vocoder.remove_weight_norm()\n",
-    "vocoder.eval() # 推理阶段不启用 batch norm 和 dropout\n",
-    "\n",
-    "stat = np.load(pwg_stat) # 读取数据预处理阶段数据集的均值和标准差\n",
+    "# 推理阶段不启用 batch norm 和 dropout\n",
+    "vocoder.eval()\n",
+    "# 读取数据预处理阶段数据集的均值和标准差\n",
+    "stat = np.load(pwg_stat)\n",
     "mu, std = stat\n",
     "mu, std = paddle.to_tensor(mu), paddle.to_tensor(std)\n",
     "pwg_normalizer = ZScore(mu, std)\n",
-    "pwg_inference = PWGInference(pwg_normalizer, vocoder) # 构建归一化的模型\n",
+    "# 构建归一化的模型\n",
+    "pwg_inference = PWGInference(pwg_normalizer, vocoder)\n",
     "pwg_inference.eval()\n",
     "print(\"Parallel WaveGAN done!\")"
    ]
@@ -1266,7 +1266,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [
     {