chore(notebook): set Expert Colab defaults to semantic + TEN VAD

For the WhisperJAV Colab Edition (Expert) notebook, change the four
pass-level default selections so the form loads with more accurate
backends selected out of the box:

  pass1_scene_detector   "automatic" -> "semantic"
  pass1_speech_segmenter "automatic" -> "ten"
  pass2_scene_detector   "automatic" -> "semantic"
  pass2_speech_segmenter "automatic" -> "ten"

Only the default values change. The dropdown choice lists themselves
are unchanged — users can still pick automatic/auditok/silero/none
for the scene detector and automatic/silero/ten/none for the speech
segmenter. The downstream map_value()/map_segmenter() helpers already
handle non-"automatic" values by emitting the corresponding CLI flags,
so Step 2 will now pass --pass1-scene-detector semantic, --pass1-speech-segmenter ten,
--pass2-scene-detector semantic, --pass2-speech-segmenter ten (or the
single-pass equivalents --scene-detection-method / --speech-segmenter
when Two-Step is off).

Both "ten" and "semantic" are supported by the CLI (verified against
--help output) and are bundled in requirements_v1.8.11.txt. The
install_colab.sh script already handles portaudio19-dev for the
TEN VAD/auditok path and warns on failure, so init failures will
degrade gracefully rather than crash.

CLI and GUI defaults are intentionally left unchanged for v1.8.11 —
they still default to auditok + silero-v3.1 for backward compatibility.
Aligning CLI and GUI Ensemble tab with these notebook defaults is
tracked for v1.8.12.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: meizhong986

notebook/WhisperJAV_colab_edition_expert.ipynb

@@ -28,8 +28,8 @@
     "pass1_model = \"automatic\" #@param [\"automatic\", \"large-v2\", \"large-v3\", \"turbo\", \"kotoba-bilingual\", \"kotoba-v2.0\", \"kotoba-v2.1\", \"kotoba-v2.2\"]\n",
     "\n",
     "#@markdown **Expert Audio Setup**\n",
-    "pass1_scene_detector = \"automatic\" #@param [\"automatic\", \"auditok\", \"silero\", \"semantic\"]\n",
-    "pass1_speech_segmenter = \"automatic\" #@param [\"automatic\", \"silero\", \"ten\", \"none\"]\n",
+    "pass1_scene_detector = \"semantic\" #@param [\"automatic\", \"auditok\", \"silero\", \"semantic\"]\n",
+    "pass1_speech_segmenter = \"ten\" #@param [\"automatic\", \"silero\", \"ten\", \"none\"]\n",
     "pass1_speech_enhancer = \"none\" #@param [\"none\", \"ffmpeg-dsp\", \"clearvoice\", \"zipenhancer\", \"bs-roformer\"]\n",
     "#@markdown <font size=\"1\">auditok=energy (fast), silero=VAD, semantic=texture (complex audio) | enhancer: ffmpeg-dsp(no GPU), clearvoice(48k), bs-roformer(vocal)</font>\n",
     "\n",
@@ -51,8 +51,8 @@
     "pass2_model = \"automatic\" #@param [\"automatic\", \"large-v2\", \"large-v3\", \"turbo\", \"kotoba-bilingual\", \"kotoba-v2.0\", \"kotoba-v2.1\", \"kotoba-v2.2\"]\n",
     "\n",
     "#@markdown **Expert Audio Setup**\n",
-    "pass2_scene_detector = \"automatic\" #@param [\"automatic\", \"auditok\", \"silero\", \"semantic\"]\n",
-    "pass2_speech_segmenter = \"automatic\" #@param [\"automatic\", \"silero\", \"ten\", \"none\"]\n",
+    "pass2_scene_detector = \"semantic\" #@param [\"automatic\", \"auditok\", \"silero\", \"semantic\"]\n",
+    "pass2_speech_segmenter = \"ten\" #@param [\"automatic\", \"silero\", \"ten\", \"none\"]\n",
     "pass2_speech_enhancer = \"none\" #@param [\"none\", \"ffmpeg-dsp\", \"clearvoice\", \"zipenhancer\", \"bs-roformer\"]\n",
     "\n",
     "#@markdown **FFmpeg Filters** *(only if enhancer is ffmpeg-dsp)*\n",
@@ -706,4 +706,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 0
-}
+}