feat(omnivoice): new TTS stack — k2-fsa/OmniVoice on irv-ml1 3090

Zero-shot, massively-multilingual (600+ language) voice-cloning + voice-design TTS (diffusion-LM, Apache-2.0). No official image, so a thin CUDA container around the pip package running upstream's own Gradio demo (no FastAPI wrapper). Pinned to GPU 0 (3090) — the A6000 is ComfyUI-exclusive — port 8199. Built + verified live on irv-ml1 (Gradio 200, container healthy). Surface is the Gradio UI + Gradio API, NOT OpenAI-compat /v1/audio/speech (wrap later if asset-engine should consume it). deploy-omnivoice.yaml builds local + verifies.
2026-06-18 22:25:54 -07:00
parent 715a68bee7
commit 984b72757f
6 changed files with 319 additions and 0 deletions
@@ -0,0 +1,110 @@
+# Deploy OmniVoice (https://github.com/k2-fsa/OmniVoice) to irv-ml1, GPU 0
+# (RTX 3090). Apache-2.0 zero-shot multilingual voice-cloning TTS, served
+# via upstream's own Gradio demo (no FastAPI wrapper).
+#
+# Builds the image locally from stacks/omnivoice/Dockerfile (CUDA 12.8 +
+# torch 2.8.0 + omnivoice from PyPI), stages the build context under
+# /opt/docker/compose/omnivoice/, brings it up, and waits for the Gradio
+# UI on :8199.
+#
+# First run is slow: ~5-10 min docker build + a one-time HF weight pre-warm
+# (k2-fsa/OmniVoice) on first container start (entrypoint.sh). The wait loop
+# below allows up to ~20 min for build-then-up + pre-warm.
+#
+# Usage:
+#   scripts/elway irv-ml1 --playbook playbooks/deploy-omnivoice.yaml
+#
+# Idempotent — every step is creates-/when-gated; rerun is safe.
+
+vars:
+  compose_dir: /opt/docker/compose/omnivoice
+  cache_dir: /worktank/omnivoice/hf_cache
+  voices_dir: /worktank/omnivoice/voices
+  host_port: "8199"
+
+steps:
+  # ── host-side dirs ──────────────────────────────────────────────────
+
+  - name: Ensure /worktank/omnivoice root exists (one-time, sudo)
+    shell: mkdir -p /worktank/omnivoice
+    sudo: true
+    creates: /worktank/omnivoice
+
+  - name: Chown /worktank/omnivoice to lkraven
+    shell: chown lkraven:lkraven /worktank/omnivoice
+    sudo: true
+    when: '[ "$(stat -c %U /worktank/omnivoice)" != lkraven ]'
+
+  - name: Ensure cache dir exists
+    shell: mkdir -p {{ cache_dir }}
+    creates: "{{ cache_dir }}"
+
+  - name: Ensure voices dir exists
+    shell: mkdir -p {{ voices_dir }}
+    creates: "{{ voices_dir }}"
+
+  - name: Ensure compose dir exists
+    shell: mkdir -p {{ compose_dir }}
+    creates: "{{ compose_dir }}"
+
+  # ── deploy build context (compose, dockerfile, entrypoint, env) ───────
+
+  - name: Upload compose.yaml
+    upload:
+      src: stacks/omnivoice/compose.yaml
+      dest: "{{ compose_dir }}/compose.yaml"
+      mode: "0644"
+
+  - name: Upload Dockerfile
+    upload:
+      src: stacks/omnivoice/Dockerfile
+      dest: "{{ compose_dir }}/Dockerfile"
+      mode: "0644"
+
+  - name: Upload entrypoint.sh
+    upload:
+      src: stacks/omnivoice/entrypoint.sh
+      dest: "{{ compose_dir }}/entrypoint.sh"
+      mode: "0755"
+
+  - name: Seed .env from template (only if absent)
+    upload:
+      src: stacks/omnivoice/.env.example
+      dest: "{{ compose_dir }}/.env"
+      mode: "0644"
+    when: "[ ! -f {{ compose_dir }}/.env ]"
+
+  # ── build + bring up ────────────────────────────────────────────────
+
+  - name: docker compose build (~5-10 min first time; cached after)
+    shell: |
+      set -o pipefail
+      cd {{ compose_dir }} && docker compose build --progress=plain 2>&1 \
+        | grep -vE '^#[0-9]+ [0-9.]+ (Downloading|Collecting|Requirement|Using cached|Installing collected|Successfully (installed|built)|━|Resolved|Prepared|Built)'
+
+  - name: docker compose up -d
+    shell: cd {{ compose_dir }} && docker compose up -d
+
+  - name: Wait for the Gradio UI to respond (allow ~20 min for weight pre-warm)
+    shell: |
+      for i in $(seq 1 240); do
+        curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/ && exit 0
+        sleep 5
+      done
+      exit 1
+    changed_when: "false"
+
+verify:
+  - name: Gradio UI returns 200
+    shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/
+    changed_when: "false"
+
+  - name: Container is running
+    shell: docker inspect omnivoice --format '{{.State.Status}}' | grep -q running
+    changed_when: "false"
+
+  - name: Container is healthy (or still starting weights)
+    shell: |
+      s=$(docker inspect omnivoice --format '{{.State.Health.Status}}' 2>/dev/null)
+      echo "health: $s"; [ "$s" = healthy ] || [ "$s" = starting ]
+    changed_when: "false"