python/voice_to_notes/services/pipeline.py

@@ -140,7 +140,7 @@ class PipelineService:
         # Step 3: Merge (or skip if diarization failed)
         if diarization is not None:
             write_message(
-                progress_message(request_id, 90, "pipeline", "Merging transcript with speakers...")
+                progress_message(request_id, 90, "merging", "Merging transcript with speakers...")
             )
             result = self._merge_results(transcription, diarization.speaker_segments)
             result.speakers = diarization.speakers

src/lib/components/ProgressOverlay.svelte

@@ -7,6 +7,38 @@
   }
 
   let { visible = false, percent = 0, stage = '', message = '' }: Props = $props();
+
+  // Map internal stage names to user-friendly labels
+  const stageLabels: Record<string, string> = {
+    'pipeline': 'Pipeline',
+    'loading_model': 'Loading Model',
+    'transcribing': 'Transcribing',
+    'loading_diarization': 'Loading Diarization',
+    'diarizing': 'Speaker Detection',
+    'done': 'Complete',
+  };
+
+  // Pipeline steps for the task list
+  const pipelineSteps = [
+    { key: 'loading_model', label: 'Load transcription model' },
+    { key: 'transcribing', label: 'Transcribe audio' },
+    { key: 'loading_diarization', label: 'Load speaker detection model' },
+    { key: 'diarizing', label: 'Identify speakers' },
+    { key: 'merging', label: 'Merge results' },
+  ];
+
+  function getStepStatus(stepKey: string, currentStage: string): 'pending' | 'active' | 'done' {
+    const stepOrder = pipelineSteps.map(s => s.key);
+    const currentIdx = stepOrder.indexOf(currentStage);
+    const stepIdx = stepOrder.indexOf(stepKey);
+
+    if (currentStage === 'done') return 'done';
+    if (stepIdx < currentIdx) return 'done';
+    if (stepIdx === currentIdx) return 'active';
+    return 'pending';
+  }
+
+  let displayStage = $derived(stageLabels[stage] || stage || 'Processing...');
 </script>
 
 {#if visible}
@@ -14,12 +46,28 @@
     <div class="progress-card">
       <div class="spinner-row">
         <div class="spinner"></div>
-        <h3>{stage || 'Processing...'}</h3>
+        <h3>{displayStage}</h3>
       </div>
-      <div class="bar-track">
+
-        <div class="bar-fill" style="width: {Math.max(percent, 2)}%"></div>
+      <div class="steps">
+        {#each pipelineSteps as step}
+          {@const status = getStepStatus(step.key, stage)}
+          <div class="step" class:step-done={status === 'done'} class:step-active={status === 'active'}>
+            <span class="step-icon">
+              {#if status === 'done'}
+                ✓
+              {:else if status === 'active'}
+                ⟳
+              {:else}
+                ·
+              {/if}
+            </span>
+            <span class="step-label">{step.label}</span>
           </div>
-      <p class="status-text">{percent}% — {message || 'Please wait...'}</p>
+        {/each}
+      </div>
+
+      <p class="status-text">{message || 'Please wait...'}</p>
       <p class="hint-text">This may take several minutes for large files</p>
     </div>
   </div>
@@ -39,7 +87,8 @@
     background: #16213e;
     padding: 2rem 2.5rem;
     border-radius: 12px;
-    min-width: 420px;
+    min-width: 380px;
+    max-width: 440px;
     color: #e0e0e0;
     border: 1px solid #2a3a5e;
     box-shadow: 0 8px 32px rgba(0, 0, 0, 0.5);
@@ -57,35 +106,52 @@
     border-top-color: #e94560;
     border-radius: 50%;
     animation: spin 0.8s linear infinite;
+    flex-shrink: 0;
   }
   @keyframes spin {
     to { transform: rotate(360deg); }
   }
   h3 {
     margin: 0;
-    text-transform: capitalize;
     font-size: 1.1rem;
   }
-  .bar-track {
+  .steps {
-    height: 10px;
+    display: flex;
-    background: #0f3460;
+    flex-direction: column;
-    border-radius: 5px;
+    gap: 0.4rem;
-    overflow: hidden;
+    margin-bottom: 1rem;
   }
-  .bar-fill {
+  .step {
-    height: 100%;
+    display: flex;
-    background: linear-gradient(90deg, #e94560, #ff6b81);
+    align-items: center;
-    transition: width 0.3s;
+    gap: 0.5rem;
-    border-radius: 5px;
+    font-size: 0.85rem;
+    color: #555;
+  }
+  .step-done {
+    color: #4ecdc4;
+  }
+  .step-active {
+    color: #e0e0e0;
+    font-weight: 500;
+  }
+  .step-icon {
+    width: 1.2rem;
+    text-align: center;
+    flex-shrink: 0;
+  }
+  .step-active .step-icon {
+    animation: spin 1.5s linear infinite;
+    display: inline-block;
   }
   .status-text {
     margin: 0.75rem 0 0;
-    font-size: 0.9rem;
+    font-size: 0.85rem;
     color: #b0b0b0;
   }
   .hint-text {
     margin: 0.5rem 0 0;
     font-size: 0.75rem;
-    color: #666;
+    color: #555;
   }
 </style>

src/lib/components/SpeakerManager.svelte

@@ -34,7 +34,11 @@
 <div class="speaker-manager">
   <h3>Speakers</h3>
   {#if $speakers.length === 0}
-    <p class="empty-hint">No speakers detected yet</p>
+    <p class="empty-hint">No speakers detected</p>
+    <p class="setup-hint">
+      Speaker detection requires a HuggingFace token.
+      Set the <code>HF_TOKEN</code> environment variable and restart.
+    </p>
   {:else}
     <ul class="speaker-list">
       {#each $speakers as speaker (speaker.id)}
@@ -78,6 +82,19 @@
   .empty-hint {
     color: #666;
     font-size: 0.875rem;
+    margin-bottom: 0.25rem;
+  }
+  .setup-hint {
+    color: #555;
+    font-size: 0.75rem;
+    line-height: 1.4;
+  }
+  .setup-hint code {
+    background: rgba(233, 69, 96, 0.15);
+    color: #e94560;
+    padding: 0.1rem 0.3rem;
+    border-radius: 3px;
+    font-size: 0.7rem;
   }
   .speaker-list {
     list-style: none;

src/lib/components/WaveformPlayer.svelte

@@ -12,6 +12,7 @@
 
   let container: HTMLDivElement;
   let wavesurfer: WaveSurfer | null = $state(null);
+  let isReady = $state(false);
   let currentTime = $state('0:00');
   let totalTime = $state('0:00');
 
@@ -39,6 +40,7 @@
     });
 
     wavesurfer.on('ready', () => {
+      isReady = true;
       const dur = wavesurfer!.getDuration();
       durationMs.set(Math.round(dur * 1000));
       totalTime = formatTime(dur);
@@ -48,6 +50,10 @@
     wavesurfer.on('pause', () => isPlaying.set(false));
     wavesurfer.on('finish', () => isPlaying.set(false));
 
+    wavesurfer.on('loading', () => {
+      isReady = false;
+    });
+
     if (audioUrl) {
       wavesurfer.load(audioUrl);
     }
@@ -57,20 +63,21 @@
     wavesurfer?.destroy();
   });
 
-  /** Toggle play/pause. Exposed for keyboard shortcuts. */
+  /** Toggle play/pause from current position. Exposed for keyboard shortcuts. */
   export function togglePlayPause() {
-    wavesurfer?.playPause();
+    if (!wavesurfer || !isReady) return;
+    wavesurfer.playPause();
   }
 
   function skipBack() {
-    if (wavesurfer) {
+    if (wavesurfer && isReady) {
       const time = Math.max(0, wavesurfer.getCurrentTime() - 5);
       wavesurfer.setTime(time);
     }
   }
 
   function skipForward() {
-    if (wavesurfer) {
+    if (wavesurfer && isReady) {
       const time = Math.min(wavesurfer.getDuration(), wavesurfer.getCurrentTime() + 5);
       wavesurfer.setTime(time);
     }
@@ -78,17 +85,20 @@
 
   /** Seek to a specific time in milliseconds. Called from transcript click-to-seek. */
   export function seekTo(timeMs: number) {
-    console.log('[voice-to-notes] seekTo called:', timeMs, 'ms, wavesurfer:', !!wavesurfer, 'duration:', wavesurfer?.getDuration());
+    if (!wavesurfer || !isReady) {
-    if (wavesurfer) {
+      console.warn('[voice-to-notes] seekTo ignored — audio not ready yet');
-      wavesurfer.setTime(timeMs / 1000);
+      return;
+    }
+    const timeSec = timeMs / 1000;
+    wavesurfer.setTime(timeSec);
     if (!wavesurfer.isPlaying()) {
       wavesurfer.play();
     }
   }
-  }
 
   /** Load a new audio file. */
   export function loadAudio(url: string) {
+    isReady = false;
     wavesurfer?.load(url);
   }
 </script>
@@ -96,11 +106,17 @@
 <div class="waveform-player">
   <div class="waveform-container" bind:this={container}></div>
   <div class="controls">
-    <button class="control-btn" onclick={skipBack} title="Back 5s">⏪</button>
+    <button class="control-btn" onclick={skipBack} title="Back 5s" disabled={!isReady}>⏪</button>
-    <button class="control-btn play-btn" onclick={togglePlayPause} title="Play/Pause">
+    <button class="control-btn play-btn" onclick={togglePlayPause} title="Play/Pause" disabled={!isReady}>
-      {#if $isPlaying}⏸{:else}▶{/if}
+      {#if !isReady}
+        ⏳
+      {:else if $isPlaying}
+        ⏸
+      {:else}
+        ▶
+      {/if}
     </button>
-    <button class="control-btn" onclick={skipForward} title="Forward 5s">⏩</button>
+    <button class="control-btn" onclick={skipForward} title="Forward 5s" disabled={!isReady}>⏩</button>
     <span class="time">{currentTime} / {totalTime}</span>
   </div>
 </div>
@@ -130,9 +146,13 @@
     cursor: pointer;
     font-size: 1rem;
   }
-  .control-btn:hover {
+  .control-btn:hover:not(:disabled) {
     background: #1a4a7a;
   }
+  .control-btn:disabled {
+    opacity: 0.4;
+    cursor: not-allowed;
+  }
   .play-btn {
     padding: 0.4rem 1rem;
     font-size: 1.2rem;

src/routes/+page.svelte

@@ -102,6 +102,7 @@
       stage: string;
       message: string;
     }>('pipeline-progress', (event) => {
+      console.log('[voice-to-notes] Progress event:', event.payload);
       const { percent, stage, message } = event.payload;
       if (typeof percent === 'number') transcriptionProgress = percent;
       if (typeof stage === 'string') transcriptionStage = stage;
@@ -387,7 +388,8 @@
     display: flex;
     gap: 1rem;
     padding: 1rem;
-    height: calc(100vh - 3.5rem);
+    height: calc(100vh - 3rem);
+    overflow: hidden;
     background: #0a0a23;
   }
   .main-content {