Web server: Add latest changes (#96)

* Init App

* init server.py (#93)

* init server.py

* Update requirements.txt

Add requirement

Co-authored-by: auau <auau@test.com>
Co-authored-by: babysor00 <babysor00@gmail.com>

* Run web.py！

Run web.py！

* Restruct readme and add instruction to use web server

* fix training preprocess of vocoder

Co-authored-by: balala <Ozgay@users.noreply.github.com>
Co-authored-by: auau <auau@test.com>

README-CN.md

@@ -53,7 +53,9 @@
 #### 2.3训练声码器 (可选)
 对效果影响不大，已经预置3款，如果希望自己训练可以参考以下命令。
 * 预处理数据:
-`python vocoder_preprocess.py <datasets_root>`
+`python vocoder_preprocess.py <datasets_root> -m <synthesizer_model_path>`
+> `<datasets_root>`替换为你的数据集目录，`<synthesizer_model_path>`替换为一个你最好的synthesizer模型目录，例如 *sythensizer\saved_mode\xxx*
+
 
 * 训练wavernn声码器:
 `python vocoder_train.py <trainid> <datasets_root>`
@@ -70,7 +72,6 @@
 `python web.py`
 运行成功后在浏览器打开地址, 默认为 `http://localhost:8080`
 <img width="578" alt="bd64cd80385754afa599e3840504f45" src="https://user-images.githubusercontent.com/7423248/134275205-c95e6bd8-4f41-4eb5-9143-0390627baee1.png">
-
 > 注：目前界面比较buggy, 
 > * 第一次点击`录制`要等待几秒浏览器正常启动录音，否则会有重音
 > * 录制结束不要再点`录制`而是`停止`
@@ -80,6 +81,7 @@
 ### 3.2 启动工具箱：
 `python demo_toolbox.py -d <datasets_root>`
 > 请指定一个可用的数据集文件路径，如果有支持的数据集则会自动加载供调试，也同时会作为手动录制音频的存储目录。
+
 <img width="1042" alt="d48ea37adf3660e657cfb047c10edbc" src="https://user-images.githubusercontent.com/7423248/134275227-c1ddf154-f118-4b77-8949-8c4c7daf25f0.png">
 
 ## Release Note
@@ -168,4 +170,6 @@ voc_pad =2
 #### 7.什么时候算训练完成？
 首先一定要出现注意力模型，其次是loss足够低，取决于硬件设备和数据集。拿本人的供参考，我的注意力是在 18k 步之后出现的，并且在 50k 步之后损失变得低于 0.4
 ![attention_step_20500_sample_1](https://user-images.githubusercontent.com/7423248/128587252-f669f05a-f411-4811-8784-222156ea5e9d.png)
+
 ![step-135500-mel-spectrogram_sample_1](https://user-images.githubusercontent.com/7423248/128587255-4945faa0-5517-46ea-b173-928eff999330.png)
+

README.md

@@ -54,7 +54,8 @@ Allowing parameter `--dataset {dataset}` to support aidatatang_200zh, magicdata,
 #### 2.3 Train vocoder (Optional)
 > note: vocoder has little difference in effect, so you may not need to train a new one.
 * Preprocess the data:
-`python vocoder_preprocess.py <datasets_root>`
+`python vocoder_preprocess.py <datasets_root> -m <synthesizer_model_path>`
+> `<datasets_root>` replace with your dataset root，`<synthesizer_model_path>`replace with directory of your best trained models of sythensizer, e.g. *sythensizer\saved_mode\xxx*
 
 * Train the wavernn vocoder:
 `python vocoder_train.py mandarin <datasets_root>`

synthesizer/hparams.py

@@ -41,7 +41,7 @@ hparams = HParams(
         tts_lstm_dims = 1024,
         tts_postnet_K = 5,
         tts_num_highways = 4,
-        tts_dropout = 0.5,
+        tts_dropout = 0.2,
         tts_cleaner_names = ["basic_cleaners"],
         tts_stop_threshold = -3.4,                  # Value below which audio generation ends.
                                                     # For example, for a range of [-4, 4], this

vocoder_preprocess.py

@@ -16,8 +16,8 @@ if __name__ == "__main__":
     parser.add_argument("datasets_root", type=str, help=\
         "Path to the directory containing your SV2TTS directory. If you specify both --in_dir and "
         "--out_dir, this argument won't be used.")
-    parser.add_argument("--model_dir", type=str, 
+    parser.add_argument("-m", "--model_dir", type=str, 
-                        default="synthesizer/saved_models/train3/", help=\
+                        default="synthesizer/saved_models/mandarin/", help=\
         "Path to the pretrained model directory.")
     parser.add_argument("-i", "--in_dir", type=str, default=argparse.SUPPRESS, help= \
         "Path to the synthesizer directory that contains the mel spectrograms, the wavs and the "