Merge branch 'main' into update-ja-jp-json

GPT_SoVITS/prepare_datasets/0-pipeline.py

@@ -1,81 +0,0 @@
-import os, torch, sys
-from subprocess import Popen
-
-now_dir = os.getcwd()
-sys.path.append(now_dir)
-from config import (
-    text_path,
-    wav_dir,
-    n_card,
-    exp_name,
-    n_parts,
-    exp_dir,
-)
-
-os.makedirs("%s/logs_s1" % exp_dir, exist_ok=True)
-os.makedirs("%s/logs_s2" % exp_dir, exist_ok=True)
-##############step1
-ps = []
-for i_part in range(n_parts):
-    cmd = "python prepare/1-get-text.py %s %s %s %s %s %s" % (
-        text_path,
-        wav_dir,
-        exp_name,
-        i_part,
-        n_parts,
-        i_part % n_card,
-    )
-    print(cmd)
-    p = Popen(cmd, shell=True)
-    ps.append(p)
-for p in ps:
-    p.wait()
-
-opt = []
-for i_part in range(n_parts):
-    txt_path = "%s/2-name2text-%s.txt" % (exp_dir, i_part)
-    with open(txt_path, "r") as f:
-        opt += f.read().strip("\n").split("\n")
-    os.remove(txt_path)
-with open("%s/2-name2text.txt" % exp_dir, "w") as f:
-    f.write("\n".join(opt) + "\n")
-
-############step2
-ps = []
-for i_part in range(n_parts):
-    cmd = "python prepare/2-get-hubert-wav32k.py %s %s %s %s %s %s" % (
-        text_path,
-        wav_dir,
-        exp_name,
-        i_part,
-        n_parts,
-        i_part % n_card,
-    )
-    print(cmd)
-    p = Popen(cmd, shell=True)
-    ps.append(p)
-for p in ps:
-    p.wait()
-#############step3
-ps = []
-for i_part in range(n_parts):
-    cmd = "python prepare/3-get-semantic.py %s %s %s %s %s" % (
-        text_path,
-        exp_name,
-        i_part,
-        n_parts,
-        i_part % n_card,
-    )
-    print(cmd)
-    p = Popen(cmd, shell=True)
-    ps.append(p)
-for p in ps:
-    p.wait()
-opt = ["item_name	semantic_audio"]
-for i_part in range(n_parts):
-    semantic_path = "%s/6-name2semantic-%s.tsv" % (exp_dir, i_part)
-    with open(semantic_path, "r") as f:
-        opt += f.read().strip("\n").split("\n")
-    os.remove(semantic_path)
-with open("%s/6-name2semantic.tsv" % exp_dir, "w") as f:
-    f.write("\n".join(opt) + "\n")

i18n/locale/en_US.json

@@ -3,7 +3,7 @@
   "UVR5已开启": "UVR5 opened ",
   "UVR5已关闭": "UVR5 closed",
   "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责. <br>如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录<b>LICENSE</b>.": "This software is open source under the MIT license. The author does not have any control over the software. Users who use the software and distribute the sounds exported by the software are solely responsible. <br>If you do not agree with this clause, you cannot use or reference any codes and files within the software package. See the root directory <b>Agreement-LICENSE.txt</b> for details.",
-  "0-前置数据集获取工具": "0-Fech dataset",
+  "0-前置数据集获取工具": "0-Fetch dataset",
   "0a-UVR5人声伴奏分离&去混响去延迟工具": "0a-UVR5 webui (for vocal separation, deecho, dereverb and denoise)",
   "是否开启UVR5-WebUI": "Open UVR5-WebUI",
   "UVR5进程输出信息": "UVR5 process output log",
@@ -128,7 +128,7 @@
   "已终止所有一键三连进程": "All one-clicking formatting tasks has been stopped",
   "已终止所有切割进程": "All audio slicing tasks has been stopped",
   "已终止所有语义token进程": "All semantics token tasks has been stopped",
-  "按中文句号。切": "按中文句号。切",
+  "按中文句号。切": "Slice by Chinese punct",
   "文本切分工具。太长的文本合成出来效果不一定好，所以太长建议先切。合成会根据文本的换行分开合成再拼起来。": "Text slicer tool, since there will be issues when infering long texts, so it is advised to cut first. When infering, it will infer respectively then combined together.",
   "文本进程执行中": "Text processing",
   "文本进程结束": "Finished text processing",

tools/my_utils.py

@@ -1,4 +1,4 @@
-import platform
+import platform,os
 import ffmpeg
 import numpy as np
 

tools/uvr5/webui.py

@@ -144,7 +144,7 @@ with gr.Blocks(title="RVC WebUI") as app:
                             minimum=0,
                             maximum=20,
                             step=1,
-                            label="人声提取激进程度",
+                            label=i18n("人声提取激进程度"),
                             value=10,
                             interactive=True,
                             visible=False,  # 先不开放调整

webui.py

@@ -171,14 +171,14 @@ def open_asr(asr_inp_dir):
     global p_asr
     if(p_asr==None):
         cmd = '"%s" tools/damo_asr/cmd-asr.py "%s"'%(python_exec,asr_inp_dir)
-        yield f"{i18n('ASR任务开启')}：%s"%cmd,{"__type__":"update","visible":False},{"__type__":"update","visible":True}
+        yield i18n("ASR任务开启：%s")%cmd,{"__type__":"update","visible":False},{"__type__":"update","visible":True}
         print(cmd)
         p_asr = Popen(cmd, shell=True)
         p_asr.wait()
         p_asr=None
         yield i18n("ASR任务完成"),{"__type__":"update","visible":True},{"__type__":"update","visible":False}
     else:
-        yield f"{i18n('已有正在进行的ASR任务，需先终止才能开启下一次任务')}",{"__type__":"update","visible":False},{"__type__":"update","visible":True}
+        yield i18n("已有正在进行的ASR任务，需先终止才能开启下一次任务"),{"__type__":"update","visible":False},{"__type__":"update","visible":True}
 
 def close_asr():
     global p_asr
@@ -212,14 +212,14 @@ def open1Ba(batch_size,total_epoch,exp_name,text_low_lr_rate,if_save_latest,if_s
         with open(tmp_config_path,"w")as f:f.write(json.dumps(data))
 
         cmd = '"%s" GPT_SoVITS/s2_train.py --config "%s"'%(python_exec,tmp_config_path)
-        yield i18n("SoVITS训练开始：%s"%cmd),{"__type__":"update","visible":False},{"__type__":"update","visible":True}
+        yield i18n("SoVITS训练开始：%s")%cmd,{"__type__":"update","visible":False},{"__type__":"update","visible":True}
         print(cmd)
         p_train_SoVITS = Popen(cmd, shell=True)
         p_train_SoVITS.wait()
         p_train_SoVITS=None
         yield i18n("SoVITS训练完成"),{"__type__":"update","visible":True},{"__type__":"update","visible":False}
     else:
-        yield f"{i18n('已有正在进行的SoVITS训练任务，需先终止才能开启下一次任务')}",{"__type__":"update","visible":False},{"__type__":"update","visible":True}
+        yield i18n("已有正在进行的SoVITS训练任务，需先终止才能开启下一次任务"),{"__type__":"update","visible":False},{"__type__":"update","visible":True}
 
 def close1Ba():
     global p_train_SoVITS
@@ -255,7 +255,7 @@ def open1Bb(batch_size,total_epoch,exp_name,if_save_latest,if_save_every_weights
         with open(tmp_config_path, "w") as f:f.write(yaml.dump(data, default_flow_style=False))
         # cmd = '"%s" GPT_SoVITS/s1_train.py --config_file "%s" --train_semantic_path "%s/6-name2semantic.tsv" --train_phoneme_path "%s/2-name2text.txt" --output_dir "%s/logs_s1"'%(python_exec,tmp_config_path,s1_dir,s1_dir,s1_dir)
         cmd = '"%s" GPT_SoVITS/s1_train.py --config_file "%s" '%(python_exec,tmp_config_path)
-        yield f"{i18n('GPT训练开始')}：%s"%cmd,{"__type__":"update","visible":False},{"__type__":"update","visible":True}
+        yield i18n("GPT训练开始：%s")%cmd,{"__type__":"update","visible":False},{"__type__":"update","visible":True}
         print(cmd)
         p_train_GPT = Popen(cmd, shell=True)
         p_train_GPT.wait()
@@ -363,7 +363,7 @@ def close1a():
             except:
                 traceback.print_exc()
         ps1a=[]
-    return i18n("已终止所有文本进程"), {"__type__": "update", "visible": True}, {"__type__": "update", "visible": False}
+    return i18n("已终止所有1a进程"), {"__type__": "update", "visible": True}, {"__type__": "update", "visible": False}
 
 ps1b=[]
 def open1b(inp_text,inp_wav_dir,exp_name,gpu_numbers,ssl_pretrained_dir):
@@ -499,11 +499,11 @@ def open1abc(inp_text,inp_wav_dir,exp_name,gpu_numbers1a,gpu_numbers1Ba,gpu_numb
                     print(cmd)
                     p = Popen(cmd, shell=True)
                     ps1abc.append(p)
-                yield i18n("文本进程执行中"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
+                yield i18n("进度：1a-ing"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
                 for p in ps1abc:p.wait()
 
                 opt = []
-                for i_part in range(all_parts):
+                for i_part in range(all_parts):#txt_path="%s/2-name2text-%s.txt"%(opt_dir,i_part)
                     txt_path = "%s/2-name2text-%s.txt" % (opt_dir, i_part)
                     with open(txt_path, "r",encoding="utf8") as f:
                         opt += f.read().strip("\n").split("\n")
@@ -511,7 +511,7 @@ def open1abc(inp_text,inp_wav_dir,exp_name,gpu_numbers1a,gpu_numbers1Ba,gpu_numb
                 with open(path_text, "w",encoding="utf8") as f:
                     f.write("\n".join(opt) + "\n")
 
-            yield i18n("文本进程结束"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
+            yield i18n("进度：1a-done"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
             ps1abc=[]
             #############################1b
             config={
@@ -536,9 +536,9 @@ def open1abc(inp_text,inp_wav_dir,exp_name,gpu_numbers1a,gpu_numbers1Ba,gpu_numb
                 print(cmd)
                 p = Popen(cmd, shell=True)
                 ps1abc.append(p)
-            yield i18n("文本进程结束, SSL提取进程执行中"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
+            yield i18n("进度：1a-done, 1b-ing"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
             for p in ps1abc:p.wait()
-            yield i18n("文本进程结束, SSL提取进程结束"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
+            yield i18n("进度：1a1b-done"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
             ps1abc=[]
             #############################1c
             path_semantic = "%s/6-name2semantic.tsv" % opt_dir
@@ -565,7 +565,7 @@ def open1abc(inp_text,inp_wav_dir,exp_name,gpu_numbers1a,gpu_numbers1Ba,gpu_numb
                     print(cmd)
                     p = Popen(cmd, shell=True)
                     ps1abc.append(p)
-                yield i18n("SSL提取进程结束, 语义token提取进程执行中"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
+                yield i18n("进度：1a1b-done, 1cing"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
                 for p in ps1abc:p.wait()
 
                 opt = ["item_name	semantic_audio"]
@@ -576,7 +576,7 @@ def open1abc(inp_text,inp_wav_dir,exp_name,gpu_numbers1a,gpu_numbers1Ba,gpu_numb
                     os.remove(semantic_path)
                 with open(path_semantic, "w",encoding="utf8") as f:
                     f.write("\n".join(opt) + "\n")
-                yield i18n("语义token提取进程结束"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
+                yield i18n("进度：all-done"), {"__type__": "update", "visible": False}, {"__type__": "update", "visible": True}
             ps1abc = []
             yield i18n("一键三连进程结束"), {"__type__": "update", "visible": True}, {"__type__": "update", "visible": False}
         except:
@@ -597,7 +597,7 @@ def close1abc():
         ps1abc=[]
     return i18n("已终止所有一键三连进程"), {"__type__": "update", "visible": True}, {"__type__": "update", "visible": False}
 
-with gr.Blocks(title="GPT-SoVITS WebUI") as app:
+with gr.Blocks(title=i18n("GPT-SoVITS WebUI")) as app:
     gr.Markdown(
         value=
             i18n("本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责. <br>如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录<b>LICENSE</b>.")