[fast_inference] 回退策略，减少padding影响，开放选项，同步代码 (#986)

* Update README

* Optimize-English-G2P

* docs: change akward expression

* docs: update Changelog_KO.md

* Fix CN punc in EN,add 's match

* Adjust normalize and g2p logic

* Update zh_CN.json

* Update README (#827)

Update README.md
Update some outdated file paths and commands

* 修复英文多音字,调整字典热加载,新增姓名匹配 (#869)

* Fix homograph dict

* Add JSON in dict

* Adjust hot dict to hot reload

* Add English name dict

* Adjust get name dict logic

* Make API Great Again (#894)

* Add zh/jp/en mix

* Optimize code readability and formatted output.

* Try OGG streaming

* Add stream mode arg

* Add media type arg

* Add cut punc arg

* Eliminate punc risk

* Update README (#895)

* Update README

* Update README

* update README

* update README

* fix typo s/Licence /License (#904)

* fix reformat cmd (#917)

Co-authored-by: starylan <starylan@outlook.com>

* Update README.md

* Normalize chinese arithmetic operations (#947)

* 改变训练和推理时的mask策略，以修复当batch_size>1时，产生的复读现象

* 同步main分支代码，增加“保持随机”选项

* 在colab中运行colab_webui.ipynb发生的uvr5模型缺失问题 (#968)

在colab中使用git下载uvr5模型时报错：
fatal: destination path 'uvr5_weights' already exists and is not an empty directory.
通过在下载前将原本从本仓库下载的uvr5_weights文件夹删除可以解决问题。

* [ASR] 修复FasterWhisper遍历输入路径失败 (#956)

* remove glob

* rename

* reset mirror pos

* 回退mask策略；
回退pad策略；
在T2SBlock中添加padding_mask，以减少pad的影响；
开放repetition_penalty参数，让用户自行调整重复惩罚的强度；
增加parallel_infer参数，用于开启或关闭并行推理，关闭时与0307版本保持一致；
在webui中增加“保持随机”选项；
同步main分支代码。

* 删除无用注释

---------

Co-authored-by: Lion <drain.daters.0p@icloud.com>
Co-authored-by: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com>
Co-authored-by: KamioRinn <snowsdream@live.com>
Co-authored-by: Pengoose <pengoose_dev@naver.com>
Co-authored-by: Yuan-Man <68322456+Yuan-ManX@users.noreply.github.com>
Co-authored-by: XXXXRT666 <157766680+XXXXRT666@users.noreply.github.com>
Co-authored-by: KamioRinn <63162909+KamioRinn@users.noreply.github.com>
Co-authored-by: Lion-Wu <130235128+Lion-Wu@users.noreply.github.com>
Co-authored-by: digger yu <digger-yu@outlook.com>
Co-authored-by: SapphireLab <36986837+SapphireLab@users.noreply.github.com>
Co-authored-by: starylan <starylan@outlook.com>
Co-authored-by: shadow01a <141255649+shadow01a@users.noreply.github.com>

GPT_SoVITS/inference_webui.py

@@ -93,8 +93,11 @@ def inference(text, text_lang,
               text_split_method, batch_size, 
               speed_factor, ref_text_free,
               split_bucket,fragment_interval,
-              seed,
+              seed, keep_random, parallel_infer,
+              repetition_penalty
               ):
+
+    seed = -1 if keep_random else seed
     actual_seed = seed if seed not in [-1, "", None] else random.randrange(1 << 32)
     inputs={
         "text": text,
@@ -112,6 +115,8 @@ def inference(text, text_lang,
         "return_fragment":False,
         "fragment_interval":fragment_interval,
         "seed":actual_seed,
+        "parallel_infer": parallel_infer,
+        "repetition_penalty": repetition_penalty,
     }
     for item in tts_pipeline.run(inputs):
         yield item, actual_seed
@@ -197,6 +202,7 @@ with gr.Blocks(title="GPT-SoVITS WebUI") as app:
                 top_k = gr.Slider(minimum=1,maximum=100,step=1,label=i18n("top_k"),value=5,interactive=True)
                 top_p = gr.Slider(minimum=0,maximum=1,step=0.05,label=i18n("top_p"),value=1,interactive=True)
                 temperature = gr.Slider(minimum=0,maximum=1,step=0.05,label=i18n("temperature"),value=1,interactive=True)
+                repetition_penalty = gr.Slider(minimum=0,maximum=2,step=0.05,label=i18n("重复惩罚"),value=1.35,interactive=True)
             with gr.Column():
                 how_to_cut = gr.Radio(
                     label=i18n("怎么切"),
@@ -205,8 +211,11 @@ with gr.Blocks(title="GPT-SoVITS WebUI") as app:
                     interactive=True,
                 )
                 with gr.Row():
-                    split_bucket = gr.Checkbox(label=i18n("数据分桶(可能会降低一点计算量，选就对了)"), value=True, interactive=True, show_label=True)
+                    parallel_infer = gr.Checkbox(label=i18n("并行推理(速度更快，但可能增大复读概率)"), value=True, interactive=True, show_label=True)
+                    split_bucket = gr.Checkbox(label=i18n("数据分桶(并行推理时会降低一点计算量)"), value=True, interactive=True, show_label=True)
                     seed = gr.Number(label=i18n("随机种子"),value=-1)
+                    keep_random = gr.Checkbox(label=i18n("保持随机"), value=True, interactive=True, show_label=True)
+
             # with gr.Column():
                 output = gr.Audio(label=i18n("输出的语音"))
                 with gr.Row():
@@ -223,7 +232,8 @@ with gr.Blocks(title="GPT-SoVITS WebUI") as app:
                 how_to_cut, batch_size, 
                 speed_factor, ref_text_free,
                 split_bucket,fragment_interval,
-                seed
+                seed, keep_random, parallel_infer,
+                repetition_penalty
              ],
             [output, seed],
         )