c84e863423
* feat: add automatic filler word removal from transcriptions Add filter_transcription_output() that removes filler words (uh, um, hmm, etc.) and hallucination patterns ([AUDIO], (pause), <tag>...</tag>) from transcriptions. Inspired by VoiceInk's approach. - Add regex-based filter in audio_toolkit/text.rs - Integrate into transcription pipeline after custom word correction - Add comprehensive tests for filler word removal - Add regex crate dependency * feat: collapse repeated 1-2 letter stutters in transcriptions Add collapse_stutters() to reduce model hallucination artifacts like "wh wh wh wh wh why" -> "wh why" or "I I I I think" -> "I think". Collapses any 1-2 letter word that repeats 3+ times consecutively to a single instance (case-insensitive matching). * remove bracket/xml stuff * format --------- Co-authored-by: CJ Pais <cj@cjpais.com>
102 lines
2.8 KiB
TOML
102 lines
2.8 KiB
TOML
[package]
|
|
name = "handy"
|
|
version = "0.6.11"
|
|
description = "Handy"
|
|
authors = ["cjpais"]
|
|
edition = "2021"
|
|
license = "MIT"
|
|
default-run = "handy"
|
|
|
|
[profile.dev]
|
|
incremental = true # Compile your binary in smaller steps.
|
|
|
|
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
|
|
|
|
[lib]
|
|
# The `_lib` suffix may seem redundant but it is necessary
|
|
# to make the lib name unique and wouldn't conflict with the bin name.
|
|
# This seems to be only an issue on Windows, see https://github.com/rust-lang/cargo/issues/8519
|
|
name = "handy_app_lib"
|
|
crate-type = ["staticlib", "cdylib", "rlib"]
|
|
|
|
# [[bin]]
|
|
# name = "cli"
|
|
# path = "src/audio_toolkit/bin/cli.rs"
|
|
|
|
[build-dependencies]
|
|
tauri-build = { version = "2", features = [] }
|
|
serde_json = "1"
|
|
serde = { version = "1", features = ["derive"] }
|
|
|
|
[dependencies]
|
|
once_cell = "1"
|
|
tauri = { version = "2.9.1", features = [
|
|
"protocol-asset",
|
|
"macos-private-api",
|
|
"tray-icon",
|
|
'image-png',
|
|
] }
|
|
tauri-plugin-log = "2.7.1"
|
|
tauri-plugin-opener = "2.5.2"
|
|
tauri-plugin-store = "2.4.1"
|
|
tauri-plugin-os = "2.3.2"
|
|
tauri-plugin-clipboard-manager = "2.3.2"
|
|
tauri-plugin-macos-permissions = "2.3.0"
|
|
tauri-plugin-process = "2.3.1"
|
|
rusqlite_migration = "2.3"
|
|
tauri-plugin-fs = "2.4.4"
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
rdev = { git = "https://github.com/rustdesk-org/rdev" }
|
|
cpal = "0.16.0"
|
|
anyhow = "1.0.95"
|
|
rubato = "0.16.2"
|
|
hound = "3.5.1"
|
|
log = "0.4.25"
|
|
env_filter = "0.1.0"
|
|
tokio = "1.43.0"
|
|
vad-rs = { git = "https://github.com/cjpais/vad-rs", default-features = false }
|
|
enigo = "0.6.1"
|
|
rodio = { git = "https://github.com/cjpais/rodio.git" }
|
|
reqwest = { version = "0.12", features = ["json", "stream"] }
|
|
futures-util = "0.3"
|
|
rustfft = "6.4.0"
|
|
strsim = "0.11.0"
|
|
natural = "0.5.0"
|
|
regex = "1"
|
|
chrono = "0.4"
|
|
rusqlite = { version = "0.37", features = ["bundled"] }
|
|
tar = "0.4.44"
|
|
flate2 = "1.0"
|
|
transcribe-rs = { version = "0.2.2", features = ["whisper", "parakeet", "moonshine"] }
|
|
ferrous-opencc = "0.2.3"
|
|
specta = "=2.0.0-rc.22"
|
|
specta-typescript = "0.0.9"
|
|
tauri-specta = { version = "=2.0.0-rc.21", features = ["derive", "typescript"] }
|
|
|
|
[target.'cfg(unix)'.dependencies]
|
|
signal-hook = "0.3"
|
|
|
|
[target.'cfg(not(any(target_os = "android", target_os = "ios")))'.dependencies]
|
|
tauri-plugin-autostart = "2.5.1"
|
|
tauri-plugin-global-shortcut = "2.3.1"
|
|
tauri-plugin-single-instance = "2.3.2"
|
|
tauri-plugin-updater = "2.9.0"
|
|
|
|
[target.'cfg(windows)'.dependencies]
|
|
windows = { version = "0.61.3", features = [
|
|
"Win32_Media_Audio_Endpoints",
|
|
"Win32_System_Com_StructuredStorage",
|
|
"Win32_System_Variant",
|
|
"Win32_Foundation",
|
|
"Win32_UI_WindowsAndMessaging",
|
|
] }
|
|
|
|
[target.'cfg(target_os = "macos")'.dependencies]
|
|
tauri-nspanel = { git = "https://github.com/ahkohd/tauri-nspanel", branch = "v2.1" }
|
|
|
|
[profile.release]
|
|
lto = true
|
|
codegen-units = 1
|
|
strip = true
|
|
panic = "abort"
|