vh
7875382aed
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).
104 lines
3.7 KiB
YAML
104 lines
3.7 KiB
YAML
# Deploy Qwen3-TTS to irv-ml1.
|
|
#
|
|
# Builds the image locally from groxaxo/Qwen3-TTS-Openai-Fastapi via
|
|
# docker buildx's git URL context (no source vendored on the host),
|
|
# stages compose + .env under /opt/docker/compose/qwen3-tts/, brings
|
|
# up, waits for /health, and verifies the web surface + MCP-irrelevant
|
|
# REST endpoints answer.
|
|
#
|
|
# First run is slow: ~3-5 min for the docker build (CUDA torch +
|
|
# transformers wheels) plus ~3-5 min for the 1.7B model download
|
|
# from HF on first inference / warmup. The healthz wait below has
|
|
# a generous deadline.
|
|
#
|
|
# Usage:
|
|
# scripts/elway irv-ml1 --playbook playbooks/deploy-qwen3-tts.yaml
|
|
#
|
|
# Idempotent — every step is creates-/when-gated; rerun is safe.
|
|
|
|
vars:
|
|
compose_dir: /opt/docker/compose/qwen3-tts
|
|
cache_dir: /worktank/qwen3-tts/cache
|
|
voices_dir: /worktank/qwen3-tts/voices
|
|
host_port: "8191"
|
|
|
|
steps:
|
|
# ── host-side dirs ──────────────────────────────────────────────────
|
|
|
|
- name: Ensure /worktank/qwen3-tts root exists (one-time, sudo)
|
|
shell: mkdir -p /worktank/qwen3-tts
|
|
sudo: true
|
|
creates: /worktank/qwen3-tts
|
|
|
|
- name: Chown /worktank/qwen3-tts to lkraven
|
|
shell: chown lkraven:lkraven /worktank/qwen3-tts
|
|
sudo: true
|
|
when: '[ "$(stat -c %U /worktank/qwen3-tts)" != 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 compose files ────────────────────────────────────────────
|
|
|
|
- name: Upload compose.yaml
|
|
upload:
|
|
src: stacks/qwen3-tts/compose.yaml
|
|
dest: "{{ compose_dir }}/compose.yaml"
|
|
mode: "0644"
|
|
|
|
- name: Seed .env from template (only if absent)
|
|
upload:
|
|
src: stacks/qwen3-tts/.env.example
|
|
dest: "{{ compose_dir }}/.env"
|
|
mode: "0644"
|
|
when: "[ ! -f {{ compose_dir }}/.env ]"
|
|
|
|
# ── build + bring up ────────────────────────────────────────────────
|
|
|
|
- name: docker compose build (~3-5 min first time; cached after)
|
|
shell: cd {{ compose_dir }} && docker compose build
|
|
|
|
- name: docker compose up -d
|
|
shell: cd {{ compose_dir }} && docker compose up -d
|
|
|
|
- name: Wait for /health to respond
|
|
# 1.7B model download on first boot can take a few minutes; allow
|
|
# up to ~10 minutes for the wait, polling every 5s.
|
|
shell: |
|
|
for i in $(seq 1 120); do
|
|
curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/health && exit 0
|
|
sleep 5
|
|
done
|
|
exit 1
|
|
changed_when: "false"
|
|
|
|
verify:
|
|
- name: /health returns 200
|
|
shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/health
|
|
changed_when: "false"
|
|
|
|
- name: /v1/models lists at least one model
|
|
shell: curl -sf http://localhost:{{ host_port }}/v1/models | grep -q '"data"\|Qwen3-TTS\|model'
|
|
changed_when: "false"
|
|
|
|
- name: /v1/voices endpoint reachable
|
|
shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/v1/voices
|
|
changed_when: "false"
|
|
|
|
- name: Web UI root serves HTML
|
|
shell: '[ "$(curl -s -o /dev/null -w %{http_code} http://localhost:{{ host_port }}/)" -eq 200 ]'
|
|
changed_when: "false"
|
|
|
|
- name: Container running + healthy or starting
|
|
shell: docker inspect qwen3-tts --format '{{.State.Status}}' | grep -q running
|
|
changed_when: "false"
|