lektor-ai/settings.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_3

# 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 = 0.8

# Ceiling on audio tokens per clip. Raise only if long clips are cut off
# mid-word.
max_tokens = 4096

# Roughly one clip in twelve comes back cut off mid-word. Those are detected and
# asked for again with a different seed, up to this many extra attempts. 0 to
# switch retrying off.
truncation_retries = 2

# 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

# Word and phrase replacements applied to the subtitles before they are spoken,
# e.g. "km/h = kilometrów na godzinę". One rule per line in that file; see the
# comments at the top of it. A relative name is looked for in the current
# directory first, then next to lektor_ai_comfy.py, so a single film can have
# its own list. A missing file is not an error.
dictionary = dictionary.txt


[normalize]
# Spell digits out as Polish words before the text reaches the TTS, in the right
# grammatical case: "Wygrał 1247 złotych" -> "Wygrał tysiąc dwieście czterdzieści
# siedem złotych". Higgs Audio misreads long digit strings and sometimes turns
# them into non-words. Standalone single digits are read correctly and are left
# alone. Runs last, on the text that goes into tts_input.srt. yes/no.
numbers = yes

# Interpreter of the normalizer's own environment — it needs transformers>=5,
# which must not be installed next to ComfyUI's pinned versions. Created by
# normalizer/setup.sh. Relative paths are resolved next to lektor_ai_comfy.py.
# If it is missing the run continues with the digits untouched.
python = normalizer/venv/bin/python

# Second model, used for the grammar of plain integers. num2words supplies the
# value (it cannot miscount) and this model puts the numeral into the right
# case: "o 250000 uchodzcach" -> "o dwustu piecdziesieciu tysiacach uchodzcow".
# The fine-tune alone gets that wrong, and sometimes loses the number itself.
# Blocks with times, dates, decimals or identifiers skip it — it is worse than
# the fine-tune on those. Leave empty to use the fine-tune for everything.
llm = normalizer/models/PLLuM-4B-instruct-2512

# Seconds to wait for one block. On a GPU a block takes well under a second;
# this only exists so a wedged worker cannot stall the whole run.
timeout = 60

# Ask ComfyUI to unload Higgs before normalizing, so the normalizer gets the
# GPU. Higgs stays resident between runs and leaves too little VRAM; a
# normalizer that does not fit spills to RAM silently and runs about 5x slower.
# ComfyUI reloads on the first clip of step 2 (20-30s, once per run). --regen
# and --rebuild never normalize, so they never pay it. yes/no.
free_comfy_vram = yes


[comfy]
# Address of the ComfyUI backend running Higgs Audio V3.
comfy_url = http://127.0.0.1:8189

# Start ComfyUI automatically when it stops answering. A crash loses its queue,
# so the clip in flight is resubmitted once the backend is back. At most 3
# attempts per run, 90s apart, so a backend that dies on startup cannot spawn an
# endless stream of terminal windows. yes/no.
autostart = yes

# The script used to start it. Relative paths are resolved next to
# lektor_ai_comfy.py.
start_command = start_comfyui.sh