use MAIN_ROOT and delete png

demos/speech_web/README.md

@@ -25,7 +25,7 @@ PaddleSpeechDemo 是一个以 PaddleSpeech 的语音交互功能为主体开发
 
 运行效果：
 
- ![效果](docs/效果展示.png)
+ ![效果](https://user-images.githubusercontent.com/30135920/191188766-12e7ca15-f7b4-45f8-9da5-0c0b0bbe5fcb.png)
 
 ## 安装
 
@@ -192,7 +192,7 @@ cd speech_server
 python vc.py --port 8010
 ```
 
-> 如果你是其它的系统，可以使用 conda 安装 mfa v2 进行体验，安装请参考 [Montreal Forced Aligner](https://montreal-forced-aligner.readthedocs.io/en/latest/getting_started.html)，使用 MFA v2 需要自行配置环境，并修改调用 MFA 相关的代码, mfa v1 与 mfa v2 使用上有差异
+如果你是其它的系统，可以使用 conda 安装 mfa v2 进行体验，安装请参考 [Montreal Forced Aligner](https://montreal-forced-aligner.readthedocs.io/en/latest/getting_started.html)，使用 MFA v2 需要自行配置环境，并修改调用 MFA 相关的代码, mfa v1 与 mfa v2 使用上有差异
 
 ### 开启前端服务
 

demos/speech_web/speech_server/src/ernie_sat.py

@@ -1,5 +1,6 @@
 import os
 
+from .util import MAIN_ROOT
 from .util import run_cmd
 
 
@@ -20,10 +21,8 @@ class SAT:
         self.cross_voc_model_path = os.path.realpath(
             "source/model/hifigan_aishell3_ckpt_0.2.0")
 
-        self.now_file_path = os.path.dirname(__file__)
+        self.BIN_DIR = os.path.join(MAIN_ROOT,
-        self.BIN_DIR = os.path.realpath(
+                                    "paddlespeech/t2s/exps/ernie_sat")
-            os.path.join(self.now_file_path,
-                         "../../../../paddlespeech/t2s/exps/ernie_sat"))
 
     def zh_synthesize_edit(self,
                            old_str: str,
@@ -37,11 +36,6 @@ class SAT:
             print("task name only in ['edit', 'synthesize']")
             return None
 
-        # 运行时的 PYTHONPATH
-        PYTHONPATH = os.path.realpath(
-            os.path.join(self.now_file_path,
-                         "../../../../examples/aishell3/ernie_sat"))
-
         # 推理文件配置
         config_path = os.path.join(self.zh_pretrain_model_path, "default.yaml")
         phones_dict = os.path.join(self.zh_pretrain_model_path,
@@ -84,9 +78,6 @@ class SAT:
                    source_lang: str,
                    target_lang: str,
                    erniesat_ckpt_name: str="snapshot_iter_489000.pdz"):
-        PYTHONPATH = os.path.realpath(
-            os.path.join(self.now_file_path,
-                         "../../../../examples/aishell3_vctk/ernie_sat"))
         # 推理文件配置
         config_path = os.path.join(self.cross_pretrain_model_path,
                                    "default.yaml")
@@ -117,9 +108,6 @@ class SAT:
                            output_name: os.PathLike,
                            task_name: str="synthesize",
                            erniesat_ckpt_name: str="snapshot_iter_199500.pdz"):
-        PYTHONPATH = os.path.realpath(
-            os.path.join(self.now_file_path,
-                         "../../../../examples/vctk/ernie_sat"))
 
         # 推理文件配置
         config_path = os.path.join(self.en_pretrain_model_path, "default.yaml")

demos/speech_web/speech_server/src/finetune.py

@@ -1,5 +1,6 @@
 import os
 
+from .util import MAIN_ROOT
 from .util import run_cmd
 
 
@@ -17,12 +18,10 @@ def find_max_ckpt(model_path):
 class FineTune:
     def __init__(self):
         self.now_file_path = os.path.dirname(__file__)
-        self.PYTHONPATH = os.path.realpath(
+        self.PYTHONPATH = os.path.join(MAIN_ROOT,
-            os.path.join(self.now_file_path,
+                                       "examples/other/tts_finetune/tts3")
-                         "../../../../examples/other/tts_finetune/tts3"))
+        self.BIN_DIR = os.path.join(MAIN_ROOT,
-        self.BIN_DIR = os.path.realpath(
+                                    "paddlespeech/t2s/exps/fastspeech2")
-            os.path.join(self.now_file_path,
-                         "../../../../paddlespeech/t2s/exps/fastspeech2"))
         self.pretrained_model_dir = os.path.realpath(
             "source/model/fastspeech2_aishell3_ckpt_1.1.0")
         self.voc_model_dir = os.path.realpath(

demos/speech_web/speech_server/src/tdnn_clone.py

@@ -1,16 +1,14 @@
 import os
 import shutil
 
+from .util import MAIN_ROOT
 from .util import run_cmd
 
 
 class VoiceCloneTDNN():
     def __init__(self):
         # Path 到指定路径上
-        self.now_file_path = os.path.dirname(__file__)
+        self.BIN_DIR = os.path.join(MAIN_ROOT, "paddlespeech/t2s/exps")
-        self.BIN_DIR = os.path.realpath(
-            os.path.join(self.now_file_path,
-                         "../../../../paddlespeech/t2s/exps"))
 
         self.am = "fastspeech2_aishell3"
         self.am_config = "source/model/fastspeech2_aishell3_ckpt_vc2_1.2.0/default.yaml"

demos/speech_web/speech_server/src/util.py

@@ -2,6 +2,9 @@ import os
 import random
 import subprocess
 
+NOW_FILE_PATH = os.path.dirname(__file__)
+MAIN_ROOT = os.path.realpath(os.path.join(NOW_FILE_PATH, "../../../../"))
+
 
 def randName(n=5):
     return "".join(random.sample('zyxwvutsrqponmlkjihgfedcba', n))