Scrub internal engineering notes from manifest _comment

v79/whisper-small.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "_comment": "Whisper-small ASR for QHexRT (more accurate, larger/slower than base). Same pipeline as whisper-base: AI Hub encoder+decoder QNN context binaries (float/fp16, sm8750/v79) + QHexRT asr_transcribe orchestrator (HF-exact 80-mel log-mel + encoder cross-KV + greedy decode). The orchestrator is size-agnostic (derives layers/heads/vocab from the bins). Tokenizer + mel filter bank are shared with base (multilingual vocab 51865, 80 mels).",
+  "_comment": "whisper-small - Qualcomm Hexagon v79 (QHexRT) deployment manifest.",
   "model": { "name": "whisper-small", "family": "asr", "dsp_arch": "v79" },
   "params": {
     "vocab": 51865, "n_layers": 12, "hidden": 768, "head_dim": 64,