使用 qwen 进行语音识别，加入 tag

Co-authored-by: Copilot <copilot@github.com>

app/aweme/[awemeId]/components/TranscriptPanel.tsx

@@ -1,6 +1,6 @@
 "use client";
 
-import { X, Copy, CheckCheck, Check } from "lucide-react";
+import { Check, CheckCheck, Copy, X } from "lucide-react";
 import { useState } from "react";
 import type { VideoTranscript } from "../types";
 
@@ -38,18 +38,23 @@ export function TranscriptPanel({
 
   if (!transcript?.speech_detected || !transcript.transcript?.length) {
     return (
-      <div
-        className="fixed inset-0 z-50 flex items-center justify-center bg-black/60 backdrop-blur-sm"
-        onClick={onClose}
-      >
+      <div className="fixed inset-0 z-50 flex items-center justify-center bg-black/60 backdrop-blur-sm">
+        <button
+          type="button"
+          aria-label="关闭"
+          className="absolute inset-0 h-full w-full cursor-default"
+          onClick={onClose}
+        />
         <div
-          className="relative w-full max-w-2xl max-h-[80vh] m-4 bg-zinc-900/95 backdrop-blur-xl border border-white/10 rounded-2xl shadow-2xl"
-          onClick={(e) => e.stopPropagation()}
+          role="dialog"
+          aria-modal="true"
+          className="relative z-10 w-full max-w-2xl max-h-[80vh] m-4 bg-zinc-900/95 backdrop-blur-xl border border-white/10 rounded-2xl shadow-2xl"
         >
           {/* 头部 */}
           <div className="flex items-center justify-between p-4 border-b border-white/10">
             <h2 className="text-lg font-semibold text-white">语音转录</h2>
             <button
+              type="button"
               onClick={onClose}
               className="p-2 rounded-full hover:bg-white/10 transition-colors"
               aria-label="关闭"
@@ -68,13 +73,17 @@ export function TranscriptPanel({
   }
 
   return (
-    <div
-      className="fixed inset-0 z-50 flex items-center justify-center bg-black/60 backdrop-blur-sm"
-      onClick={onClose}
-    >
+    <div className="fixed inset-0 z-50 flex items-center justify-center bg-black/60 backdrop-blur-sm">
+      <button
+        type="button"
+        aria-label="关闭"
+        className="absolute inset-0 h-full w-full cursor-default"
+        onClick={onClose}
+      />
       <div
-        className="relative w-full max-w-2xl max-h-[80vh] m-4 bg-zinc-900/95 backdrop-blur-xl border border-white/10 rounded-2xl shadow-2xl flex flex-col"
-        onClick={(e) => e.stopPropagation()}
+        role="dialog"
+        aria-modal="true"
+        className="relative z-10 w-full max-w-2xl max-h-[80vh] m-4 bg-zinc-900/95 backdrop-blur-xl border border-white/10 rounded-2xl shadow-2xl flex flex-col"
       >
         {/* 头部 */}
         <div className="flex items-center justify-between p-4 border-b border-white/10 flex-shrink-0">
@@ -85,9 +94,22 @@ export function TranscriptPanel({
                 语言: {transcript.language}
               </p>
             )}
+            {transcript.content_tags?.length > 0 && (
+              <div className="mt-2 flex flex-wrap gap-1.5">
+                {transcript.content_tags.map((tag) => (
+                  <span
+                    key={tag}
+                    className="rounded bg-blue-500/15 px-2 py-0.5 text-xs text-blue-200"
+                  >
+                    {tag}
+                  </span>
+                ))}
+              </div>
+            )}
           </div>
           <div className="flex items-center gap-2">
             <button
+              type="button"
               onClick={handleCopyAll}
               className="flex items-center gap-2 px-3 py-2 text-sm bg-blue-600/20 text-blue-300 rounded-lg hover:bg-blue-600/30 transition-colors"
             >
@@ -104,6 +126,7 @@ export function TranscriptPanel({
               )}
             </button>
             <button
+              type="button"
               onClick={onClose}
               className="p-2 rounded-full hover:bg-white/10 transition-colors"
               aria-label="关闭"
@@ -117,9 +140,8 @@ export function TranscriptPanel({
         <div className="flex-1 overflow-y-auto p-4 space-y-2">
           {transcript.transcript.map((text, index) => (
             <div
-              key={index}
-              className="group bg-white/5 rounded-lg p-3 hover:bg-white/10 transition-colors cursor-pointer"
-              onClick={() => handleCopy(text, index)}
+              key={`${index}-${text}`}
+              className="group bg-white/5 rounded-lg p-3 hover:bg-white/10 transition-colors"
             >
               <div className="flex items-start justify-between gap-3">
                 <div className="flex-1 min-w-0">
@@ -133,8 +155,9 @@ export function TranscriptPanel({
                   </p>
                 </div>
                 <button
+                  type="button"
                   onClick={() => handleCopy(text, index)}
-                  className="flex-shrink-0 p-2 rounded-lg opacity-0 group-hover:opacity-100 hover:bg-white/10 transition-all"
+                  className="flex-shrink-0 p-2 rounded-lg opacity-0 group-hover:opacity-100 focus:opacity-100 hover:bg-white/10 transition-all"
                   aria-label="复制"
                 >
                   {copiedIndex === index ? (

app/aweme/[awemeId]/types.ts

@@ -56,6 +56,7 @@ export type VideoTranscript = {
   speech_detected: boolean;
   language: string | null;
   transcript: string[];
+  content_tags: string[];
 };
 
 export type Neighbors = {