feat(chatterbox-fast): Phase 3 scaffold — Dockerfile, compose, .env.example

Container artifacts to deploy alongside the live chatterbox (:8196) on irv-ml1. - Dockerfile: thin overlay FROM local/chatterbox:v1 (sibling's image, has the chatterbox lib + torch + fastapi) + COPY scheduler.py app.py; runs uvicorn. - compose.yaml: mirrors the sibling chatterbox stack (runtime: nvidia + NVIDIA_VISIBLE_DEVICES; host IP:port, no traefik-net — these GPU TTS services aren't traefik-fronted). Port 8197, /health healthcheck, homepage labels, reuses /worktank/chatterbox/{cache,reference_audio}. - .env.example: GPU default device 1 (A6000) — turbo is fp32, 3090 free VRAM is tight; port reservations; perf-lever toggles. Not yet deployed — awaiting operator go (shared GPU host, runs beside production).
2026-06-01 23:30:36 -07:00
parent a95aa75947
commit 5c8d174f8e
4 changed files with 135 additions and 1 deletions
@@ -0,0 +1,55 @@
+# chatterbox-fast — custom streaming TTS server (sub-second time-to-first-audio
+# via adaptive buffer-ratchet chunking on Chatterbox-Turbo). Deployed ALONGSIDE
+# the live `chatterbox` (:8196) on irv-ml1 — burn in, then flip the catalog.
+#
+# Convention note: mirrors the sibling `chatterbox` stack on this host — GPU via
+# `runtime: nvidia` + NVIDIA_VISIBLE_DEVICES (not the repo's generic device_ids),
+# and accessed by host IP:port (no traefik-net; these GPU TTS services aren't
+# traefik-fronted). Kept consistent with the proven sibling over the generic rule.
+#
+# All tunables live in .env — edit that, not this file.
+
+services:
+  chatterbox-fast:
+    image: local/chatterbox-fast:${CBF_TAG:-v1}
+    build:
+      context: .
+      dockerfile: Dockerfile
+      args:
+        CHATTERBOX_BASE: local/chatterbox:${CBF_BASE_TAG:-v1}
+    container_name: chatterbox-fast
+    restart: unless-stopped
+    runtime: nvidia
+    ports:
+      - "${CBF_BIND:-0.0.0.0}:${CBF_PORT:-8197}:8197"
+    environment:
+      # GPU pin. Default device 1 (A6000) — turbo loads fp32 (~not the fp16 old
+      # notes assumed), so the 3090's tight free VRAM may not fit; see .env.example.
+      - NVIDIA_VISIBLE_DEVICES=${CBF_GPU_DEVICES:-1}
+      - HF_HOME=/app/hf_cache
+      - CBF_MODEL_DEVICE=cuda
+      - CBF_VOICES_DIR=/refs
+      - CBF_DEFAULT_VOICE=${CBF_DEFAULT_VOICE:-glados_25s}
+      - CBF_BIND=0.0.0.0
+      - CBF_PORT=8197
+      - CBF_TF32=${CBF_TF32:-1}
+      - CBF_SDPA_FLASH=${CBF_SDPA_FLASH:-1}
+    volumes:
+      - ${CBF_REFERENCE_DIR:-/worktank/chatterbox/reference_audio}:/refs
+      - ${CBF_CACHE_DIR:-/worktank/chatterbox/cache}:/app/hf_cache
+    healthcheck:
+      # Our app exposes /health → {"status":"ok",...} once the model is loaded.
+      # python urllib (devnen base ships no curl); strip spaces so the match is
+      # formatting-agnostic. 127.0.0.1 explicitly (uvicorn binds IPv4 only).
+      test: ["CMD-SHELL", "python3 -c \"import urllib.request,sys; b=urllib.request.urlopen('http://127.0.0.1:8197/health',timeout=5).read(); sys.exit(0 if b'\\\"status\\\":\\\"ok\\\"' in b.replace(b' ',b'') else 1)\""]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      # Weights are HF-cached already (~16s load measured); generous anyway.
+      start_period: 120s
+    labels:
+      - homepage.group=AI Systems
+      - homepage.name=Chatterbox Fast
+      - homepage.icon=mdi-account-music-outline
+      - homepage.description=Streaming TTS — sub-second first-audio, adaptive-chunk (irv-ml1)
+      - homepage.href=http://10.100.79.3:${CBF_PORT:-8197}