Upload app.py with huggingface_hub

app.py

@@ -357,7 +357,7 @@ def transcribe_full(audio_file, language_name, num_speakers,
     filename = Path(audio_path).name
     lang_code = LANGUAGE_MAP.get(language_name, None)
 
-    progress(0.05, desc="Transkripsi di GPU...")
+    progress(0.05, desc="⏳ Menunggu GPU & memproses audio... (bisa 30-90 detik)")
 
     # 1. Transcribe on GPU
     t0 = time.time()
@@ -372,11 +372,11 @@ def transcribe_full(audio_file, language_name, num_speakers,
         raise gr.Error("Tidak ada teks yang terdeteksi dari audio.")
 
     transcribe_time = time.time() - t0
-    progress(0.60, desc=f"Transkripsi selesai ({transcribe_time:.0f}s)")
+    progress(0.60, desc=f"✅ Transkripsi selesai ({transcribe_time:.0f}s)")
 
     # 2. Speaker Diarization (CPU)
     if enable_diarization and len(segments) >= 2:
-        progress(0.65, desc="Mengidentifikasi pembicara...")
+        progress(0.65, desc="🔍 Mengidentifikasi pembicara...")
         try:
             segments = perform_diarization(audio_path, segments, num_speakers)
             segments = merge_consecutive(segments)
@@ -390,7 +390,7 @@ def transcribe_full(audio_file, language_name, num_speakers,
             seg['speaker'] = 'Speaker 1'
             seg['speaker_id'] = 0
 
-    progress(0.85, desc="Membuat file output...")
+    progress(0.85, desc="📄 Membuat file output...")
 
     # 3. Export
     timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
@@ -404,7 +404,7 @@ def transcribe_full(audio_file, language_name, num_speakers,
     generate_txt(segments, txt_path, filename, detected_lang, duration)
     generate_docx(segments, docx_path, filename, detected_lang, duration)
 
-    progress(0.95, desc="Menyiapkan hasil...")
+    progress(0.95, desc="📦 Menyiapkan hasil...")
 
     # Build display text
     transcript_lines = []
@@ -432,7 +432,7 @@ def transcribe_full(audio_file, language_name, num_speakers,
         f"| Engine | Whisper + ZeroGPU H200 |"
     )
 
-    progress(1.0, desc="Selesai!")
+    progress(1.0, desc="🎉 Selesai!")
     return summary, transcript_text, srt_path, txt_path, docx_path
 
 
@@ -807,7 +807,75 @@ span[data-testid="info-text"] {
 }
 """
 
-with gr.Blocks(theme=THEME, title="TranscribeAI", css=CUSTOM_CSS) as demo:
+UPLOAD_PROGRESS_JS = """
+<style>
+#upload-bar-wrap{display:none;position:fixed;top:0;left:0;right:0;z-index:99999;height:5px;background:#222228}
+#upload-bar{height:100%;width:0%;background:linear-gradient(90deg,#6366f1,#a78bfa);transition:width .2s;border-radius:0 3px 3px 0}
+#upload-pct{display:none;position:fixed;top:12px;right:16px;z-index:99999;background:#1a1a1f;border:1px solid #6366f1;
+color:#c7c7ff;padding:7px 16px;border-radius:10px;font-size:13px;font-weight:700;font-family:Inter,sans-serif;
+box-shadow:0 4px 20px rgba(99,102,241,.3)}
+</style>
+<script>
+(function(){
+  var barW=document.createElement('div');barW.id='upload-bar-wrap';
+  barW.innerHTML='<div id="upload-bar"></div>';document.body.appendChild(barW);
+  var pctEl=document.createElement('div');pctEl.id='upload-pct';document.body.appendChild(pctEl);
+
+  function show(p){
+    barW.style.display='block';pctEl.style.display='block';
+    document.getElementById('upload-bar').style.width=p+'%';
+    pctEl.textContent='\\u{1F4E4} Uploading... '+p+'%';
+  }
+  function hide(){
+    show(100);
+    setTimeout(function(){
+      barW.style.display='none';pctEl.style.display='none';
+      document.getElementById('upload-bar').style.width='0%';
+    },800);
+  }
+
+  var _fetch=window.fetch;
+  window.fetch=function(input,init){
+    var url=typeof input==='string'?input:(input&&input.url?input.url:'');
+    if(url.indexOf('/upload')!==-1 && init && init.method==='POST' && init.body){
+      return new Promise(function(resolve,reject){
+        var xhr=new XMLHttpRequest();
+        xhr.open('POST',url,true);
+        xhr.responseType='text';
+        if(init.headers){
+          try{
+            var h=init.headers instanceof Headers?init.headers:new Headers(init.headers);
+            h.forEach(function(v,k){
+              if(k.toLowerCase()!=='content-type')xhr.setRequestHeader(k,v);
+            });
+          }catch(e){}
+        }
+        xhr.upload.onprogress=function(e){
+          if(e.lengthComputable)show(Math.round(e.loaded/e.total*100));
+        };
+        xhr.onload=function(){
+          hide();
+          var headers=new Headers();
+          try{
+            xhr.getAllResponseHeaders().trim().split('\\r\\n').forEach(function(line){
+              var i=line.indexOf(':');
+              if(i>0)headers.append(line.slice(0,i).trim(),line.slice(i+1).trim());
+            });
+          }catch(e){}
+          resolve(new Response(xhr.responseText,{status:xhr.status,statusText:xhr.statusText,headers:headers}));
+        };
+        xhr.onerror=function(){hide();reject(new TypeError('Network request failed'));};
+        xhr.onabort=function(){hide();reject(new DOMException('Aborted','AbortError'));};
+        xhr.send(init.body);
+      });
+    }
+    return _fetch.apply(this,arguments);
+  };
+})();
+</script>
+"""
+
+with gr.Blocks(theme=THEME, title="TranscribeAI", css=CUSTOM_CSS, head=UPLOAD_PROGRESS_JS) as demo:
 
     # ---- Header ----
     gr.HTML("""