vh
131d746c92
Three fixes from the second-wave deploy attempts:
* voxtral: vllm/vllm-omni doesn't publish a `latest` tag — pull
failed with "manifest unknown". Pinned VOXTRAL_VLLM_TAG to v0.18.0
(released 2026-03-29, the day after the Voxtral 4B TTS release —
first cut with Voxtral support).
* kyutai-tts: NillPointer wrapper exposes ONLY /health (root) and
POST /v1/audio/speech. No /v1/models, no /v1/audio/voices —
those return 404. Verified by /openapi.json against the live
container. Compose healthcheck + playbook wait + verify steps
all repointed at the actual paths. POST /v1/audio/speech is now
smoke-tested with a RIFF WAV assertion (same pattern as fish-s2).
* fish-s2: added FISH_S2_MODEL env var so the model variant is
swappable via .env without rebuilding. Both s2-pro (default) and
s1-mini are pre-pulled into the bind-mount; LLAMA_CHECKPOINT_PATH
+ DECODER_CHECKPOINT_PATH now use ${FISH_S2_MODEL:-s2-pro}.
s1-mini was originally gated on fishaudio's HF org (401), but
niobures/OpenAudio-S1 mirrors the same files openly — pulled
from there via a one-shot snapshot_download.
60 lines
3.0 KiB
Bash
60 lines
3.0 KiB
Bash
# Fish Audio S2-Pro stack tunables. Copy to `.env` on irv-ml1 before
|
||
# deploying.
|
||
|
||
# ── build pin ────────────────────────────────────────────────────────
|
||
# SHA of fishaudio/fish-speech to build from. Bump + rebuild when you
|
||
# want upstream wrapper updates. Use the FULL 40-char SHA — docker
|
||
# buildx's git source resolver doesn't accept short hashes.
|
||
FISH_S2_SHA=main
|
||
|
||
# Local image tag — bump when you change build context to force a
|
||
# fresh layer build.
|
||
FISH_S2_TAG=v1
|
||
|
||
# ── network ──────────────────────────────────────────────────────────
|
||
# Host port (container listens on 8080 internally; we map to 8195
|
||
# externally to fit alongside the rest of the irv-ml1 TTS slate).
|
||
# Port reservations on irv-ml1: 8188 ComfyUI, 8190 CosyVoice, 8191
|
||
# Qwen3-TTS, 8192 IndexTTS-2, 8193 Kokoro, 8194 VibeVoice, 8196
|
||
# Chatterbox, 8765 Parakeet ASR.
|
||
FISH_S2_PORT=8195
|
||
FISH_S2_BIND=0.0.0.0
|
||
|
||
# ── runtime / GPU ────────────────────────────────────────────────────
|
||
# GPU pinning. "0" = RTX 3090 (24 GB), "1" = RTX A6000 (48 GB), "all"
|
||
# = both visible. Fish S2-Pro consumes ~17 GB during inference (4B
|
||
# model + KV cache), so the A6000 is the right home with comfortable
|
||
# headroom. The 3090's 24 GB CAN fit it but leaves ~5 GB for KV which
|
||
# is tight for long contexts.
|
||
FISH_S2_GPU_DEVICES=1
|
||
|
||
# torch.compile on first inference of each shape adds ~60 s warmup but
|
||
# unlocks ~10× speedup per upstream. Worth it for sustained use; flip
|
||
# to 0 to disable if you hit a torch.compile bug on a future
|
||
# checkpoint.
|
||
FISH_S2_COMPILE=1
|
||
|
||
# Model variant. Both checkpoints are pre-pulled by the deploy
|
||
# playbook into /worktank/fish-s2/checkpoints/. Swap by editing this
|
||
# value + `docker compose up -d --force-recreate` (no rebuild needed).
|
||
# s2-pro — 4B-class, highest quality, ~7-8 s TTFB on a long phrase
|
||
# s1-mini — lighter, ~3-5× smaller model.pth, expected ~2-3 s TTFB
|
||
# fishaudio/s1-mini on HF is gated, but niobures/OpenAudio-S1 mirrors
|
||
# the same files openly — playbook pulls from there.
|
||
FISH_S2_MODEL=s2-pro
|
||
|
||
# ── persistent storage on the host ───────────────────────────────────
|
||
# Model checkpoints — Fish auto-downloads s2-pro on first run (~9 GB
|
||
# at BF16) and caches under here. Persistent across container
|
||
# recreates so we don't re-pull.
|
||
FISH_S2_CHECKPOINT_DIR=/worktank/fish-s2/checkpoints
|
||
|
||
# Reference audio for voice cloning. Drop clean ~5-15 s clips here
|
||
# (WAV / FLAC / MP3); the wrapper scans on request. One clean clip
|
||
# per voice; name them descriptively.
|
||
FISH_S2_REFERENCE_DIR=/worktank/fish-s2/references
|
||
|
||
# HF cache — persistent across container recreates to skip the model
|
||
# re-pull. Worth ~9 GB on disk.
|
||
FISH_S2_CACHE_DIR=/worktank/fish-s2/hf_cache
|