mirror of
https://github.com/storytold/filmcraft.git
synced 2026-10-28 20:17:58 -06:00
Manuel CamachoandClaude Opus 5.5
beebdbcd39
- filmcraft-tts (feature kokoro): Kokoro-82M on candle, implemented from
the StyleTTS 2 / iSTFTNet / ALBERT papers, config.json and the
checkpoint's tensor shapes; official .pth read with candle's restricted
pickle reader; voice packs from their zip. Neural Voice: tts-text
phonemize -> Kokoro per chunk -> pauses -> pitch via audio-dsp.
- catalog: 9 US English voices (model card grade C+ or better) + CMUdict,
every file pinned to a revision and SHA-256 (336 MB).
- speech: generic download_files (same verified downloader).
- engine: tts.render (background synthesis into Session::tts_cache),
tts.downloadVoices (background job, cancellable), voices list with
package state; feature neural-voices (default on in the desktop app).
- ui: natural/basic voice groups, consent box (size, sources, licences),
download progress + Cancel, synthesis never blocks the window;
ui.set {tts:{...}} for agents.
Measured: Whisper-base WER on 50 original sentences 2.1-3.6 % for all 9
voices (built-in robotic voice 96.6 %); 2.2-2.3x real time on CPU.
Gates: fmt, clippy, layers, assets, wasm pass; tests pass except
shortcuts_tests::assign_reassigns_conflicts_and_undoes (fails on main)
and the frame pool test (flaky under load, passes alone).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
34 lines
1.2 KiB
TOML
34 lines
1.2 KiB
TOML
[package]
|
|
name = "filmcraft-tts"
|
|
description = "FilmCraft text to speech: the Voice trait, the voice catalogue, script parsing (pause markers), the built-in formant voice and (feature kokoro) Kokoro-82M neural voices on candle"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
rust-version.workspace = true
|
|
|
|
[lints]
|
|
workspace = true
|
|
|
|
[features]
|
|
default = []
|
|
# Kokoro-82M neural voices on the CPU via candle (pure Rust). Off by default and in wasm builds.
|
|
kokoro = ["dep:candle-core", "dep:candle-nn", "dep:zip", "dep:serde_json", "dep:filmcraft-tts-text", "dep:filmcraft-audio-dsp"]
|
|
|
|
[dependencies]
|
|
filmcraft-tts-text = { workspace = true, optional = true }
|
|
filmcraft-audio-dsp = { workspace = true, optional = true }
|
|
serde = { workspace = true }
|
|
thiserror = { workspace = true }
|
|
candle-core = { version = "0.9", default-features = false, optional = true }
|
|
candle-nn = { version = "0.9", default-features = false, optional = true }
|
|
zip = { version = "7", default-features = false, optional = true }
|
|
serde_json = { workspace = true, optional = true }
|
|
|
|
[[example]]
|
|
name = "kokoro_say"
|
|
required-features = ["kokoro"]
|
|
|
|
[[example]]
|
|
name = "narrate"
|
|
required-features = ["kokoro"]
|