Jeena
c6f2e7c46d
Streaming typed every phrase as soon as a 250ms pause came along, which made long dictations trickle in slowly and double-emitted the last phrase (once as the phrase, once in the final flush — the source of the phantom "Thank you."). With phrase_silence_ms at 5s, phrases only flush at the very end, so the whole text lands in one piece about 0.1s after the key is released. The 20s force-split still emits during very long continuous speech, so nothing is lost there.
23 lines
No EOL
752 B
TOML
23 lines
No EOL
752 B
TOML
[audio]
|
|
device = "pipewire"
|
|
|
|
[input]
|
|
# pi's Ink TUI drops injected keystrokes while it is busy streaming output;
|
|
# raise the inter-key delay so dictation survives that.
|
|
key_delay_ms = 10
|
|
|
|
[general]
|
|
backend = "local-whisper"
|
|
language = "en"
|
|
silence_timeout_ms = 6000
|
|
notify = true
|
|
audio_feedback = true
|
|
|
|
[local-whisper]
|
|
model_path = "/home/jeena/.local/share/whisrs/models/ggml-base.en.bin"
|
|
# Batch-like: phrases only flush after 5s of silence, so text lands in one
|
|
# piece right after the key is released (0.1s decode) instead of trickling in
|
|
# while the hold key is still down — injection during a held modifier is
|
|
# unreliable. The 20s force-split still emits during very long continuous
|
|
# speech, so nothing is lost there.
|
|
phrase_silence_ms = 5000 |