mARTin-B78/tts-voice-creator-clone-and-design-2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Raise audiobook casting timeouts to 10min/5min for large models (v1.14.8)

Browse Source 
Was 6min/3min. 122B+ models can take longer than that just to produce
a first token; 10min also happens to match the server-side cap
(_request_timeout_seconds), so this is the max without raising that too.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
mARTin-B78 2026-07-09 00:09:04 +02:00
parent c969150095
commit 8d5050bb80
4 changed files with 15 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
CHANGELOG.md
View File

@ -9,6 +9,13 @@ Follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) · versioned wi
---
## [1.14.8] — 2026-07-09
### Changed
- **Audiobook casting timeouts raised for large/slow models** — first attempt per passage: 6 min → 10 min; half-passage retry: 3 min → 5 min. 10 min also matches the server's own timeout cap, so this is the practical maximum without also raising that cap.
---
## [1.14.7] — 2026-07-08
### Fixed

2
VERSION
View File

@ -1 +1 @@
1.14.7
1.14.8

6
static/index.html
View File

@ -10,7 +10,7 @@
<meta name="format-detection" content="telephone=no">
<meta name="color-scheme" content="light dark">
<meta name="theme-color" content="#2563EB">
<meta name="app-version" content="1.14.7">
<meta name="app-version" content="1.14.8">
<link rel="manifest" href="/manifest.webmanifest">
<link rel="icon" href="/static/icon.svg" type="image/svg+xml">
<link rel="apple-touch-icon" href="/static/icon.svg">
@ -27,7 +27,7 @@
<!-- ── Core styles (local — no CDN dependency for first paint) ────────── -->
<link rel="stylesheet" href="/static/vendor/mdi/materialdesignicons.min.css">
<link rel="stylesheet" href="/static/style.css?v=1.14.7">
<link rel="stylesheet" href="/static/style.css?v=1.14.8">
<!-- ── Flag icons — non-blocking (loaded async, icons appear after JS) ── -->
@ -365,7 +365,7 @@ window.toggleNavTree = function(treeId, chevronId) {
</script>
<!-- loader.js: fetches sections → loads JS modules → removes skeleton -->
<script src="/static/loader.js?v=1.14.7"></script>
<script src="/static/loader.js?v=1.14.8"></script>
</body>
</html>

7
static/js/audiobook.js
View File

@ -15,9 +15,10 @@ const AUDIOBOOK_CHUNK_CHARS = 3000; // passage size per LLM attribution call
const AUDIOBOOK_WARMUP_TIMEOUT_MS = 240000;
// A chunk's max_tokens (routes/conversation.py) can reach ~4000 on slow local models
// (~15 tok/s on modest hardware), i.e. up to ~4.5 minutes of pure generation time —
// the old 90s timeout aborted almost every passage before the model finished.
const AUDIOBOOK_ATTRIBUTION_TIMEOUT_MS = 360000;
const AUDIOBOOK_ATTRIBUTION_RETRY_TIMEOUT_MS = 180000;
// and large (100B+) models can take even longer just to produce a first token.
// 600s is also the server-side cap (_request_timeout_seconds in routes/conversation.py).
const AUDIOBOOK_ATTRIBUTION_TIMEOUT_MS = 600000;
const AUDIOBOOK_ATTRIBUTION_RETRY_TIMEOUT_MS = 300000;
const AUDIOBOOK_RECAST_TIMEOUT_MS = 240000;
const AUDIOBOOK_RECAST_CONTEXT_CHARS = 4200;
const AUDIOBOOK_RECAST_TARGETS_PER_CALL = 6;