27331d66e4
Image default is beam 5 on x86 (1 on ARM). Benchmarked on framework-pt (i5-1135G7, base-int8, real speech): beam 1 transcribes identical text ~45% faster; extra CPU threads made it slower, so only the beam changes. App revision 3.4.2 > image 3.4.1 so catalog-driven nodes roll the args change; a 3.4.1-1 suffix would semver-compare LOWER and never ship. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
79 lines
2.7 KiB
YAML
79 lines
2.7 KiB
YAML
app:
|
|
id: pine-whisper
|
|
name: Pine Whisper (STT)
|
|
# App revision 3.4.2 = upstream wyoming-whisper 3.4.1 image + tuned args
|
|
# (--beam-size 1). Bumped past the image version so catalog-driven nodes
|
|
# pick up the args change; the pre-release form "3.4.1-1" would compare
|
|
# LOWER than 3.4.1 under semver and never roll out.
|
|
version: "3.4.2"
|
|
description: Wyoming-protocol faster-whisper speech-to-text engine. Internal Pine voice-assistant stack member — turns speech captured by a PineVoice satellite into text for Home Assistant Assist.
|
|
category: home
|
|
|
|
# Hyphen name matches the runtime references (stack member table / startup
|
|
# order) + the live container, so on an existing node the orchestrator ADOPTS
|
|
# the running engine rather than recreating it (downloaded models under /data
|
|
# preserved).
|
|
container_name: pine-whisper
|
|
|
|
container:
|
|
image: docker.io/rhasspy/wyoming-whisper:3.4.1
|
|
pull_policy: if-not-present
|
|
network: archy-net
|
|
network_aliases: [pine-whisper]
|
|
# The image entrypoint already binds tcp://0.0.0.0:10300; these args only
|
|
# pick the model + language (mirrors the pine ha-stack.yml compose command).
|
|
# --beam-size 1: the image default is 5 on x86 (1 on ARM). Benchmarked on
|
|
# framework-pt (i5-1135G7, base-int8): beam 1 transcribes the same text
|
|
# ~45% faster — the standard low-latency setting for short voice commands
|
|
# (HA's own whisper add-on defaults to 1).
|
|
custom_args: ["--model", "base-int8", "--language", "en", "--beam-size", "1"]
|
|
|
|
dependencies:
|
|
- storage: 2Gi
|
|
|
|
resources:
|
|
memory_limit: 2Gi
|
|
|
|
security:
|
|
# cap-drop=ALL is applied by the orchestrator. A plain Python Wyoming server
|
|
# on an unprivileged port needs no added capabilities.
|
|
capabilities: []
|
|
readonly_root: false # downloads the whisper model into /data on first run
|
|
no_new_privileges: true
|
|
network_policy: isolated
|
|
|
|
ports:
|
|
# Published so Home Assistant (on the pasta net) can reach the engine via
|
|
# host.containers.internal:10300 (the Wyoming integration endpoint).
|
|
- host: 10300
|
|
container: 10300
|
|
protocol: tcp
|
|
|
|
volumes:
|
|
- type: bind
|
|
source: /var/lib/archipelago/pine-whisper
|
|
target: /data
|
|
options: [rw]
|
|
|
|
environment: []
|
|
|
|
health_check:
|
|
type: tcp
|
|
endpoint: localhost:10300
|
|
interval: 30s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 60s # first start downloads the model
|
|
|
|
metadata:
|
|
author: Rhasspy / Home Assistant
|
|
icon: /assets/img/app-icons/pine.svg
|
|
website: https://github.com/rhasspy/wyoming-faster-whisper
|
|
repo: https://github.com/rhasspy/wyoming-faster-whisper
|
|
license: MIT
|
|
tags:
|
|
- home
|
|
- voice
|
|
- speech-to-text
|
|
- wyoming
|