claudeandClaude Opus 5
3dde6e58e4
Poll interval wait_for_completion() polled every 3 s, which quantised every clip to a 3 s boundary — across 2075 existing clips, 91% of the gaps landed exactly on a multiple of 3 s. It now starts at 0.25 s and backs off to 2 s after 10 s, so short clips are picked up immediately without hammering the server on long ones. Measured over 34 clips: 4.75 s actual vs 6.35 s under the old poll, a 25% cut in TTS wait (~18 min on a 693-clip episode). Runs now print real generation time, e.g. "done (4.2s)". A WebSocket would remove polling entirely but needs a third-party client, which would cost this script its dependency-free property. settings.ini voice, speed, temperature, max_tokens, strip_leading_ms, trailing_fade_ms, orig_volume, tts_volume, output_dir and comfy_url moved to an INI file next to the script. Precedence is CLI flag > settings.ini > built-in default, wired by feeding loaded values in as argparse defaults. --settings FILE selects an alternative profile. INI rather than TOML (tomllib is 3.11+, this runs on system Python 3.10) or JSON (no comments). A missing, partial, malformed or corrupt file degrades to built-in defaults with a warning instead of killing a long run. Run-specific flags are deliberately excluded: --start, --end, --seed, --regen, --rebuild, --resume-from, --embedded-subs, --skip-tts. Per-job folders All state for one video now lives in <output_dir>/clips/<video name>/ — clips, tts_input.srt, tts_assembled.flac, embedded_sub.srt and video_fragment.mkv. Only <stem>_lektor.mkv stays at the top level. tts_input.srt moved with the clips because they are a matched pair: block N in the SRT is clip_NNNN.flac. Previously both sat at the top level and each new job overwrote the last one's, so rebuilding an older film silently paired its clips with the newest film's text. Any past job can now be rebuilt. A run against the old flat layout gets an explanatory message. gudowski/ -> voices/ VOICE_PROMPTS_DIR is now resolved relative to the script rather than hardcoded, so moving the project no longer breaks it. Voice filenames are unchanged, so --voice gudowski_short still works. Docs updated throughout for the new layout, settings file and poll behaviour. Known issue, not addressed here: with a non-zero --start the voiceover plays early. extract_video_fragment() stream-copies, so it can only cut on a keyframe and seeks backwards to it, while TTS timestamps are relative to the requested start. On S01_E08 at --start 07:40 the nearest earlier keyframe is 458.375 s, putting the voiceover 1.625 s ahead of the picture. Runs with --start 00:00 are unaffected, since 0 is always a keyframe. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
57 lines
1.9 KiB
INI
57 lines
1.9 KiB
INI
# lektor_ai_comfy — default settings
|
|
#
|
|
# These are the values used when a flag is not given on the command line.
|
|
# Precedence: command-line flag > this file > built-in defaults
|
|
#
|
|
# Delete a line (or the whole file) to fall back to the built-in default.
|
|
# A malformed value is reported and ignored, never fatal.
|
|
#
|
|
# Not configurable here, because they belong to a single run rather than to
|
|
# your setup: --start --end --seed --regen --rebuild --resume-from
|
|
# --embedded-subs --skip-tts
|
|
|
|
|
|
[tts]
|
|
# Voice reference. Either a name in voices/ (expects NAME.wav + NAME.txt),
|
|
# or a full path to a .wav file.
|
|
voice = gudowski_short
|
|
|
|
# Per-clip speed-up applied with atempo, before assembly.
|
|
# Raise it if speech regularly overruns its subtitle window; 1.0 = no change.
|
|
speed = 1.2
|
|
|
|
# Sampling temperature. 1.0 makes the model occasionally recite the reference
|
|
# transcript instead of the subtitle; 0.9 largely prevents that. Lower is more
|
|
# deterministic but flatter.
|
|
temperature = 0.7
|
|
|
|
# Ceiling on audio tokens per clip. Raise only if long clips are cut off
|
|
# mid-word.
|
|
max_tokens = 4096
|
|
|
|
# Trim this many ms from the start of every clip, to remove an inhale artifact.
|
|
# Try 80-150 if you hear one. Too high clips the first consonant.
|
|
strip_leading_ms = 0
|
|
|
|
# Fade out the last N ms of every clip to suppress tail pops. 0 disables.
|
|
trailing_fade_ms = 80
|
|
|
|
|
|
[mix]
|
|
# Levels inside the Polish lektor track only. Track 0 is always the untouched
|
|
# original, so mixing aggressively here costs you nothing.
|
|
# Dialogue-heavy sources: orig 0.5 / tts 2.0. Quiet sources: orig 1.0 / tts 1.4.
|
|
orig_volume = 0.70
|
|
tts_volume = 1.4
|
|
|
|
|
|
[paths]
|
|
# Where clips, assembled audio and the finished video are written.
|
|
# Relative paths are resolved from wherever you run the script.
|
|
output_dir = output
|
|
|
|
|
|
[comfy]
|
|
# Address of the ComfyUI backend running Higgs Audio V3.
|
|
comfy_url = http://127.0.0.1:8189
|