diff --git a/enjoy/src/renderer/components/medias/media-caption-tabs.tsx b/enjoy/src/renderer/components/medias/media-caption-tabs.tsx
index baaab66e..800ba74d 100644
--- a/enjoy/src/renderer/components/medias/media-caption-tabs.tsx
+++ b/enjoy/src/renderer/components/medias/media-caption-tabs.tsx
@@ -227,7 +227,7 @@ const SelectedTabContent = (props: {
           <div className="select-text">
             {camdictResult.posItems.map((posItem, index) => (
               <div key={index} className="mb-4">
-                <div className="flex items-center space-x-4 mb-2">
+                <div className="flex items-center space-x-4 mb-2 flex-wrap">
                   <div className="italic text-sm text-muted-foreground">
                     {posItem.type}
                   </div>
diff --git a/enjoy/src/renderer/hooks/use-transcriptions.tsx b/enjoy/src/renderer/hooks/use-transcriptions.tsx
index 23be3764..2e3f1ac8 100644
--- a/enjoy/src/renderer/hooks/use-transcriptions.tsx
+++ b/enjoy/src/renderer/hooks/use-transcriptions.tsx
@@ -123,7 +123,7 @@ export const useTranscriptions = (media: AudioType | VideoType) => {
                 type: 'token',
                 text: '-',
                 startTime: sentence.timeline[j - 1].endTime,
-                endTime: token.startTime,
+                endTime: sentence.timeline[j - 1].endTime,
                 timeline: [],
               })
               return;