stacks: parakeet healthcheck (curl→wget); qwen3-tts variant labels

- parakeet/compose.yaml: healthcheck was using curl which isn't in the
  image (only wget is, via apt). 2,190 failing checks — switched to
  `wget -q -O /dev/null`, container went healthy on recreate.
- qwen3-tts/.env.example: variant annotation was reversed. The upstream
  wrapper's runtime error is unambiguous: voice cloning requires the
  -Base variant, not -CustomVoice. Corrected the comment block and
  flipped the default to Qwen/Qwen3-TTS-12Hz-1.7B-Base.
- qwen3-tts/README.md: 0.6B switch snippet now suffixes -Base too,
  since plain `Qwen/Qwen3-TTS-12Hz-0.6B` isn't published on HF.

stacks/parakeet/compose.yaml

@@ -38,7 +38,8 @@ services:
     volumes:
       - ${PARAKEET_MODELS_DIR}:/models
     healthcheck:
-      test: ["CMD-SHELL", "curl -fsS http://localhost:8000/healthz >/dev/null || exit 1"]
+      # Image ships wget (apt) but not curl — use wget so the check actually runs.
+      test: ["CMD-SHELL", "wget -q -O /dev/null http://localhost:8000/healthz || exit 1"]
       interval: 30s
       timeout: 10s
       retries: 3

stacks/qwen3-tts/.env.example

@@ -26,13 +26,15 @@ QWEN3_TTS_BIND=0.0.0.0
 QWEN3_TTS_BACKEND=official
 
 # Model variant. Upstream publishes four checkpoints on HF:
-#   Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice — flagship, voice cloning
+#   Qwen/Qwen3-TTS-12Hz-1.7B-Base        — flagship, supports voice cloning
-#   Qwen/Qwen3-TTS-12Hz-1.7B-Base        — flagship, no cloning
+#   Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice — flagship, preset voices only
-#   Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice — lightweight, voice cloning
+#   Qwen/Qwen3-TTS-12Hz-0.6B-Base        — lightweight, supports voice cloning
-#   Qwen/Qwen3-TTS-12Hz-0.6B-Base        — lightweight, no cloning
+#   Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice — lightweight, preset voices only
 # 1.7B = ~6–8 GB VRAM bfloat16, best quality. 0.6B = ~2–3 GB.
-# Use -CustomVoice for `voice="clone:<name>"` to work.
+# `voice="clone:<name>"` only works with the -Base variants — that's
-QWEN3_TTS_MODEL=Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
+# what the upstream wrapper enforces. Earlier versions of this file
+# had the variant labels reversed; corrected 2026-04-24.
+QWEN3_TTS_MODEL=Qwen/Qwen3-TTS-12Hz-1.7B-Base
 
 # Warm the model on container start so the first synthesis request
 # doesn't pay the load latency. Adds ~30 s to startup. Recommended.

stacks/qwen3-tts/README.md

@@ -95,7 +95,7 @@ If 1.7B is too heavy or you need to share GPUs more aggressively:
 ```bash
 ssh irv-ml1 '
   cd /opt/docker/compose/qwen3-tts && \
-  sed -i "s|^QWEN3_TTS_MODEL=.*|QWEN3_TTS_MODEL=Qwen/Qwen3-TTS-12Hz-0.6B|" .env && \
+  sed -i "s|^QWEN3_TTS_MODEL=.*|QWEN3_TTS_MODEL=Qwen/Qwen3-TTS-12Hz-0.6B-Base|" .env && \
   docker compose up -d
 '
 ```