Update inference_webui.py

inference_webui.py

@@ -478,12 +478,12 @@ def get_tts_wav(
         prompt_text = prompt_text.strip("\n")
         if prompt_text[-1] not in splits:
             prompt_text += "。" if prompt_language != "en" else "."
-        print(i18n("实际输入的参考文本:").key, prompt_text)
+        print(i18n("实际输入的参考文本:"), prompt_text)
     text = text.strip("\n")
     if text[0] not in splits and len(get_first(text)) < 4:
         text = "。" + text if text_language != "en" else "." + text
 
-    print(i18n("实际输入的目标文本:").key, text)
+    print(i18n("实际输入的目标文本:"), text)
     zero_wav = np.zeros(
         int(hps.data.sampling_rate * 0.3),
         dtype=np.float16 if is_half == True else np.float32,
@@ -527,7 +527,7 @@ def get_tts_wav(
         text = cut5(text)
     while "\n\n" in text:
         text = text.replace("\n\n", "\n")
-    print(i18n("实际输入的目标文本(切句后):").key, text)
+    print(i18n("实际输入的目标文本(切句后):"), text)
     texts = text.split("\n")
     texts = process_text(texts)
     texts = merge_short_text_in_array(texts, 5)
@@ -543,9 +543,9 @@ def get_tts_wav(
             continue
         if text[-1] not in splits:
             text += "。" if text_language != "en" else "."
-        print(i18n("实际输入的目标文本(每句):").key, text)
+        print(i18n("实际输入的目标文本(每句):"), text)
         phones2, bert2, norm_text2 = get_phones_and_bert(text, text_language, version)
-        print(i18n("前端处理后的文本(每句):").key, norm_text2)
+        print(i18n("前端处理后的文本(每句):"), norm_text2)
         if not ref_free:
             bert = torch.cat([bert1, bert2], 1)
             all_phoneme_ids = torch.LongTensor(phones1 + phones2).to(device).unsqueeze(0)