fix(dots-tts): v2 — curly-punctuation sanitize + sentence-chunking

Curly apostrophes (ratatoskr's LLM emits typographic punctuation) made dots
mispronounce contractions ("Donut's"->"donut ess"); fold curly->ASCII before
synth, keep normalize_text on. Add server-side sentence-chunking so long turns
stop truncating at dots' ~40s single-generate cap (verified full 160s Zev).
Dockerfile: pin dots.tts==0.2.1 + torch/torchaudio==2.8.0 (upstream constraints
now pin a phantom gradio==6.17.0; float torchaudio->2.11.0 crashes the load).
This commit is contained in:
vh
2026-08-10 09:11:56 -07:00
parent d3727dee53
commit 10d379db5b
4 changed files with 77 additions and 10 deletions
+5 -1
View File
@@ -1,7 +1,10 @@
# dots-tts stack tunables. Copy to `.env` on irv-ml1 before deploying.
# ── image ────────────────────────────────────────────────────────────
DOTS_TAG=v1
# v2 (2026-08-10): curly->ASCII sanitize (fixes "Donut's"->"donut ess" on
# typographic apostrophes) + server-side sentence-chunking (long turns no longer
# truncate at dots' ~40s single-generate cap).
DOTS_TAG=v2
# ── network ──────────────────────────────────────────────────────────
DOTS_BIND=0.0.0.0
@@ -17,6 +20,7 @@ DOTS_MODEL=dots-studio/dots.tts-soar
DOTS_DEFAULT_VOICE=donut
DOTS_NUM_STEPS=10 # 10 = full quality @ RTF ~0.22; lower = faster/rougher
DOTS_GUIDANCE_SCALE=1.2
DOTS_CHUNK_MAX_CHARS=280 # max chars per generate() chunk (dots caps ~40s/~500 patches)
# ── host mounts ──────────────────────────────────────────────────────
# HF cache holding the downloaded soar snapshot (~5GB). Reuse the burn-in cache.