diff --git a/enjoy/src/renderer/components/medias/media-caption.tsx b/enjoy/src/renderer/components/medias/media-caption.tsx
index 7b997db3..533dca10 100644
--- a/enjoy/src/renderer/components/medias/media-caption.tsx
+++ b/enjoy/src/renderer/components/medias/media-caption.tsx
@@ -39,7 +39,7 @@ export const MediaCaption = () => {
     setTranscriptionDraft,
     ipaMappings,
   } = useContext(MediaPlayerProviderContext);
-  const { EnjoyApp } = useContext(AppSettingsProviderContext);
+  const { EnjoyApp, learningLanguage } = useContext(AppSettingsProviderContext);
   const [activeIndex, setActiveIndex] = useState<number>(0);
   const [selectedIndices, setSelectedIndices] = useState<number[]>([]);
   const [multiSelecting, setMultiSelecting] = useState<boolean>(false);
@@ -415,9 +415,13 @@ export const MediaCaption = () => {
                   const ipas = word.timeline.map((t) =>
                     t.timeline.map((s) => s.text).join("")
                   );
-                  return `${word.text}(${convertWordIpaToNormal(ipas, {
-                    mappings: ipaMappings,
-                  }).join("")})`;
+                  return `${word.text}(${
+                    learningLanguage.startsWith("en")
+                      ? convertWordIpaToNormal(ipas, {
+                          mappings: ipaMappings,
+                        }).join("")
+                      : ipas.join("")
+                  })`;
                 })
                 .join(" ");
 
@@ -477,16 +481,19 @@ export const Caption = (props: {
   } = props;
 
   const { currentNotes, ipaMappings } = useContext(MediaPlayerProviderContext);
+  const { learningLanguage } = useContext(AppSettingsProviderContext);
   const notes = currentNotes.filter((note) => note.parameters?.quoteIndices);
   const [notedquoteIndices, setNotedquoteIndices] = useState<number[]>([]);
 
   let words = caption.text.split(" ");
   const ipas = caption.timeline.map((w) =>
     w.timeline.map((t) =>
-      convertWordIpaToNormal(
-        t.timeline.map((s) => s.text),
-        { mappings: ipaMappings }
-      ).join("")
+      learningLanguage.startsWith("en")
+        ? convertWordIpaToNormal(
+            t.timeline.map((s) => s.text),
+            { mappings: ipaMappings }
+          ).join("")
+        : t.text
     )
   );
 
diff --git a/enjoy/src/renderer/components/medias/media-captions/tab-content-translation.tsx b/enjoy/src/renderer/components/medias/media-captions/tab-content-translation.tsx
index 1c3beb90..ac18c15f 100644
--- a/enjoy/src/renderer/components/medias/media-captions/tab-content-translation.tsx
+++ b/enjoy/src/renderer/components/medias/media-captions/tab-content-translation.tsx
@@ -80,12 +80,14 @@ const SelectedWords = (props: {
                   >
                     {word.timeline
                       .map((t) =>
-                        convertWordIpaToNormal(
-                          t.timeline.map((s) => s.text),
-                          {
-                            mappings: ipaMappings,
-                          }
-                        ).join("")
+                        learningLanguage.startsWith("en")
+                          ? convertWordIpaToNormal(
+                              t.timeline.map((s) => s.text),
+                              {
+                                mappings: ipaMappings,
+                              }
+                            ).join("")
+                          : t.text
                       )
                       .join(" ")}
                   </span>
diff --git a/enjoy/src/renderer/context/media-player-provider.tsx b/enjoy/src/renderer/context/media-player-provider.tsx
index 8a90e8ca..bfa84d8f 100644
--- a/enjoy/src/renderer/context/media-player-provider.tsx
+++ b/enjoy/src/renderer/context/media-player-provider.tsx
@@ -123,7 +123,9 @@ export const MediaPlayerProvider = ({
   children: React.ReactNode;
 }) => {
   const minPxPerSec = 150;
-  const { EnjoyApp, webApi } = useContext(AppSettingsProviderContext);
+  const { EnjoyApp, webApi, learningLanguage } = useContext(
+    AppSettingsProviderContext
+  );
 
   const [layout, setLayout] = useState<{
     name: string;
@@ -340,7 +342,9 @@ export const MediaPlayerProvider = ({
           );
           labels[index] = [
             labels[index] || "",
-            convertIpaToNormal(phone.text.trim()),
+            learningLanguage.startsWith("en")
+              ? convertIpaToNormal(phone.text.trim())
+              : phone.text.trim(),
           ].join("");
         });
       }
diff --git a/enjoy/src/utils.ts b/enjoy/src/utils.ts
index db927ee2..64ead8c2 100644
--- a/enjoy/src/utils.ts
+++ b/enjoy/src/utils.ts
@@ -84,13 +84,23 @@ export const convertWordIpaToNormal = (
 
     let j = i - 1;
     for (; j > 0 && j > i - 2; j--) {
-      if (consonantsRegex.test(ipas[j]) && !consonantsRegex.test(ipas[j - 1])) {
+      if (
+        consonantsRegex.test(converted[j]) &&
+        !IPA_CONSONANTS.trill.includes(converted[j]) &&
+        !IPA_CONSONANTS.approximant.includes(converted[j]) &&
+        !IPA_CONSONANTS.lateralApproximant.includes(converted[j])
+      )
+        break;
+      if (
+        consonantsRegex.test(converted[j]) &&
+        !consonantsRegex.test(converted[j - 1])
+      ) {
         break;
       }
     }
 
     if (isVowel && mark) {
-      if (ipas[j]) {
+      if (converted[j] && consonantsRegex.test(converted[j])) {
         converted[j] = mark[0] + converted[j];
       } else {
         converted[i] = mark[0] + converted[i];