qwen3-tts: add stack + deploy playbook for irv-ml1

Alibaba's open-weight TTS (Apache 2.0, Jan 2026), deployed via groxaxo/Qwen3-TTS-Openai-Fastapi wrapper. Built locally from a pinned git SHA via docker buildx's git context — no source vendored. 1.7B flagship model by default; 0.6B available via QWEN3_TTS_MODEL env override. Why we need a second TTS stack: cosyvoice 3 emits Chinese phonemes for English content per upstream FunAudioLLM/CosyVoice#1790 (unfixed). Qwen3-TTS is from the same Alibaba team but with English first-class in the checkpoint — 10 languages, 97 ms streaming TTFB, instruction-driven emotion. Coexists with cosyvoice on irv-ml1 (port 8191; cosyvoice keeps 8190). Voice cloning shape DIFFERS from cosyvoice: profile-based, not voice-id. Profiles live under voice_library/profiles/<name>/ and are referenced as voice="clone:<name>". Path layout: /worktank/qwen3-tts/{cache,voices}/, with cache excluded from restic (regenerable from HF Hub) and voices included (cloned profiles need original reference audio to recreate). playbooks/deploy-qwen3-tts.yaml: 10 steps + 5 verify, idempotent; the wait step polls /health for up to ~10 min to absorb first-run model download. Stack only — restic profile update for /worktank/qwen3-tts/voices/ to follow when this is empirically validated against the GLaDOS voice (the "did Qwen inherit the Chinese-bias bug?" question).
2026-04-24 16:58:19 -07:00
parent 8f6c364f47
commit 7875382aed
4 changed files with 321 additions and 0 deletions
@@ -0,0 +1,52 @@
+# Qwen3-TTS stack tunables. Copy to `.env` on irv-ml1 before deploying.
+
+# ── build pin ────────────────────────────────────────────────────────
+# SHA of groxaxo/Qwen3-TTS-Openai-Fastapi to build from. Bump + rebuild
+# when you want upstream wrapper updates.
+QWEN3_TTS_SHA=10323ce778c48a75dbda93d0a4891983fb371f58
+
+# Local image tag — bump when you change build context to force a
+# fresh layer build.
+QWEN3_TTS_TAG=v1
+
+# ── network ──────────────────────────────────────────────────────────
+# Host port (container listens on 8880 internally).
+QWEN3_TTS_PORT=8191
+
+# Bind address. 0.0.0.0 exposes on all interfaces (incl. WG tunnel
+# interface 10.100.79.3); 127.0.0.1 restricts to local-only.
+QWEN3_TTS_BIND=0.0.0.0
+
+# ── runtime ──────────────────────────────────────────────────────────
+# Inference backend. `official` = default upstream; `optimized` =
+# faster but slightly less robust; `vllm_omni` = vLLM-backed (needs
+# more VRAM); `pytorch` = bare pytorch path.
+QWEN3_TTS_BACKEND=official
+
+# Model variant. 1.7B = flagship, 6–8 GB VRAM with bfloat16, best
+# quality + control. 0.6B = lightweight, ~2–3 GB VRAM, faster, slightly
+# less expressive.
+QWEN3_TTS_MODEL=Qwen/Qwen3-TTS-12Hz-1.7B
+
+# Warm the model on container start so the first synthesis request
+# doesn't pay the load latency. Adds ~30 s to startup. Recommended.
+QWEN3_TTS_WARMUP=true
+
+# Concurrency cap on synthesis requests. Single GPU + 1.7B model →
+# leave at 1 unless you're load-testing.
+QWEN3_TTS_MAX_CONCURRENT=1
+
+# Mount the gradio voice-studio UI at /voice-studio for browser-side
+# voice cloning. Set "false" to disable for headless deployments.
+QWEN3_TTS_VOICE_STUDIO=true
+
+# ── persistent storage on the host ───────────────────────────────────
+# HuggingFace cache (model weights, ~5 GB after first run). Bind-mounted
+# so model state survives container recreate. Excluded from restic
+# (regenerable from HF Hub).
+QWEN3_TTS_CACHE_DIR=/worktank/qwen3-tts/cache
+
+# Cloned voice profiles (meta.json + reference.wav per voice). Precious
+# — cloned voices need the original reference audio to recreate.
+# Included in restic.
+QWEN3_TTS_VOICES_DIR=/worktank/qwen3-tts/voices