rust-toolchain.toml pins to stable 1.94.1 so contributors and CI runners share the exact rustc / rustfmt / clippy versions. Without the pin, every machine surfaces a different lint set depending on its local install — six pre-existing lints showed up on 1.94.1 that 1.93-era HANDOVER reported clean. Clippy fixes (all pre-existing, not introduced by feature work): - crates/storage/src/database.rs: std::iter::repeat().take() -> repeat_n() - crates/llm/src/lib.rs (docs): "+ frontends" was parsed as a markdown bullet continuation by rustdoc, breaking doc-lazy-continuation. Reworded to "and". - crates/llm/src/lib.rs (loop): while-let-on-iterator -> for-loop. - src-tauri/src/commands/security.rs: .iter().any(|a| *a == x) -> .contains(&x). - src-tauri/src/lib.rs: io::Error::new(Other, e) -> io::Error::other(e). - src-tauri/src/tauri_app_data_migration.rs: drop function-tail `return`s inside cfg blocks; each platform's block now ends with a tail expression. cargo fmt sweep across the workspace. Mechanical layout-only changes; no semantics affected. Workspace gates after this commit: - cargo fmt --check: clean - cargo clippy --workspace --all-targets -- -D warnings: clean - cargo test --workspace: 405/0 (will become 409/0 with Phase A.1+A.2)
247 lines
8.7 KiB
Rust
247 lines
8.7 KiB
Rust
// Streaming resampler used by the live transcription session.
|
|
//
|
|
// Microphones expose whatever native rate the device supports (commonly
|
|
// 44 100 or 48 000 Hz). whisper.cpp wants 16 kHz mono `f32`. The live
|
|
// session calls `push_samples()` with each capture chunk as it arrives
|
|
// and gets back zero-or-more 16 kHz samples to enqueue into the model
|
|
// input buffer. At end-of-session it calls `flush()` once to drain any
|
|
// residual input and the resampler's internal tail.
|
|
//
|
|
// Implementation notes:
|
|
//
|
|
// - We use rubato's `SincFixedIn` (same engine the file-level
|
|
// `resample::resample_to_16khz` uses) so behaviour stays consistent
|
|
// across live + file paths.
|
|
// - rubato's fixed-in API requires a constant-size input chunk. We
|
|
// buffer captured samples in a residual `Vec<f32>` and only feed
|
|
// the resampler when we have a full chunk.
|
|
// - When the input rate already matches 16 kHz we skip rubato
|
|
// entirely and pass samples straight through (zero allocations
|
|
// beyond the returned `Vec`).
|
|
// - `flush()` zero-pads the residual to one final chunk, processes
|
|
// it, then truncates the output to the proportion that came from
|
|
// real (non-padded) samples — otherwise the trailing silence
|
|
// produced by the padding leaks into the saved audio file.
|
|
|
|
use rubato::{
|
|
Resampler, SincFixedIn, SincInterpolationParameters, SincInterpolationType, WindowFunction,
|
|
};
|
|
|
|
use lumotia_core::constants::WHISPER_SAMPLE_RATE;
|
|
use lumotia_core::error::{Error, Result};
|
|
|
|
/// Number of input samples the rubato resampler consumes per `process()`
|
|
/// call. Matches the chunk size used in `resample::resample_to_16khz`.
|
|
const INPUT_CHUNK: usize = 1024;
|
|
|
|
pub enum StreamingResampler {
|
|
/// Source is already at 16 kHz — emit input verbatim.
|
|
Passthrough,
|
|
/// Source is at some other rate — feed via rubato.
|
|
Sinc {
|
|
resampler: SincFixedIn<f32>,
|
|
residual: Vec<f32>,
|
|
ratio: f64,
|
|
},
|
|
}
|
|
|
|
impl StreamingResampler {
|
|
/// Construct a resampler that converts `from_rate` Hz mono input to
|
|
/// 16 kHz mono output. Returns an error if `from_rate` is zero or if
|
|
/// rubato rejects the requested ratio.
|
|
pub fn new(from_rate: u32) -> Result<Self> {
|
|
if from_rate == 0 {
|
|
return Err(Error::AudioDecodeFailed(
|
|
"StreamingResampler: input sample rate is 0".into(),
|
|
));
|
|
}
|
|
|
|
if from_rate == WHISPER_SAMPLE_RATE {
|
|
return Ok(Self::Passthrough);
|
|
}
|
|
|
|
let ratio = WHISPER_SAMPLE_RATE as f64 / from_rate as f64;
|
|
|
|
let params = SincInterpolationParameters {
|
|
sinc_len: 256,
|
|
f_cutoff: 0.95,
|
|
oversampling_factor: 128,
|
|
interpolation: SincInterpolationType::Cubic,
|
|
window: WindowFunction::Blackman,
|
|
};
|
|
|
|
let resampler = SincFixedIn::<f32>::new(
|
|
ratio,
|
|
1.1, // max relative jitter; mirrors the file-level resampler
|
|
params,
|
|
INPUT_CHUNK,
|
|
1, // mono
|
|
)
|
|
.map_err(|e| Error::AudioDecodeFailed(format!("StreamingResampler init failed: {e}")))?;
|
|
|
|
Ok(Self::Sinc {
|
|
resampler,
|
|
residual: Vec::new(),
|
|
ratio,
|
|
})
|
|
}
|
|
|
|
/// Feed a fresh capture chunk and return any 16 kHz samples that are
|
|
/// ready to dispatch. The caller may pass any length; samples that
|
|
/// don't yet form a complete `INPUT_CHUNK` are buffered internally
|
|
/// and emitted on a later call (or on `flush()`).
|
|
pub fn push_samples(&mut self, mono: &[f32]) -> Result<Vec<f32>> {
|
|
match self {
|
|
Self::Passthrough => Ok(mono.to_vec()),
|
|
Self::Sinc {
|
|
resampler,
|
|
residual,
|
|
..
|
|
} => {
|
|
if mono.is_empty() {
|
|
return Ok(Vec::new());
|
|
}
|
|
residual.extend_from_slice(mono);
|
|
|
|
let mut out: Vec<f32> = Vec::new();
|
|
while residual.len() >= INPUT_CHUNK {
|
|
let chunk: Vec<f32> = residual.drain(..INPUT_CHUNK).collect();
|
|
let input = vec![chunk];
|
|
let result = resampler.process(&input, None).map_err(|e| {
|
|
Error::AudioDecodeFailed(format!("StreamingResampler process failed: {e}"))
|
|
})?;
|
|
if let Some(channel) = result.into_iter().next() {
|
|
out.extend_from_slice(&channel);
|
|
}
|
|
}
|
|
Ok(out)
|
|
}
|
|
}
|
|
}
|
|
|
|
/// Drain any residual samples and return the final 16 kHz output.
|
|
/// Called once when the live session is stopping. Subsequent calls
|
|
/// return an empty `Vec`.
|
|
pub fn flush(&mut self) -> Result<Vec<f32>> {
|
|
match self {
|
|
Self::Passthrough => Ok(Vec::new()),
|
|
Self::Sinc {
|
|
resampler,
|
|
residual,
|
|
ratio,
|
|
} => {
|
|
if residual.is_empty() {
|
|
return Ok(Vec::new());
|
|
}
|
|
|
|
let leftover = residual.len();
|
|
let mut chunk = std::mem::take(residual);
|
|
chunk.resize(INPUT_CHUNK, 0.0);
|
|
|
|
let input = vec![chunk];
|
|
let result = resampler.process(&input, None).map_err(|e| {
|
|
Error::AudioDecodeFailed(format!("StreamingResampler flush failed: {e}"))
|
|
})?;
|
|
|
|
let Some(mut out) = result.into_iter().next() else {
|
|
return Ok(Vec::new());
|
|
};
|
|
|
|
// Trim padding-induced output: keep only the proportion
|
|
// of samples that came from real input, not from the
|
|
// zeros we used to fill the chunk.
|
|
let real_out = ((leftover as f64) * *ratio).round() as usize;
|
|
if real_out < out.len() {
|
|
out.truncate(real_out);
|
|
}
|
|
Ok(out)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
fn resampled_sine_rms(from_rate: u32, input_frequency: f32) -> f64 {
|
|
let sample_count = from_rate as usize;
|
|
let samples: Vec<f32> = (0..sample_count)
|
|
.map(|i| {
|
|
let t = i as f32 / from_rate as f32;
|
|
(std::f32::consts::TAU * input_frequency * t).sin()
|
|
})
|
|
.collect();
|
|
|
|
let mut resampler = StreamingResampler::new(from_rate).unwrap();
|
|
let mut produced = Vec::new();
|
|
for chunk in samples.chunks(997) {
|
|
produced.extend(resampler.push_samples(chunk).unwrap());
|
|
}
|
|
produced.extend(resampler.flush().unwrap());
|
|
|
|
(produced.iter().map(|&s| (s as f64).powi(2)).sum::<f64>() / produced.len() as f64).sqrt()
|
|
}
|
|
|
|
#[test]
|
|
fn passthrough_at_16khz() {
|
|
let mut r = StreamingResampler::new(16_000).unwrap();
|
|
let out = r.push_samples(&[0.1, 0.2, 0.3]).unwrap();
|
|
assert_eq!(out, vec![0.1, 0.2, 0.3]);
|
|
assert!(r.flush().unwrap().is_empty());
|
|
}
|
|
|
|
#[test]
|
|
fn rejects_zero_rate() {
|
|
assert!(StreamingResampler::new(0).is_err());
|
|
}
|
|
|
|
#[test]
|
|
fn high_frequency_content_is_filtered_before_downsampling() {
|
|
let rms = resampled_sine_rms(48_000, 12_000.0);
|
|
assert!(
|
|
rms < 0.01,
|
|
"12kHz content must be low-pass filtered before 16kHz output with at least ~40dB attenuation; rms={rms}"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn near_nyquist_content_is_attenuated_before_downsampling() {
|
|
let rms = resampled_sine_rms(48_000, 9_000.0);
|
|
assert!(
|
|
rms < 0.05,
|
|
"9kHz content just above 16kHz Nyquist should be materially attenuated; rms={rms}"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn streaming_48k_to_16k_preserves_duration() {
|
|
let from_rate = 48_000u32;
|
|
let secs = 1.0;
|
|
let n = (from_rate as f64 * secs) as usize;
|
|
let samples: Vec<f32> = (0..n).map(|i| (i as f32 * 0.001).sin()).collect();
|
|
|
|
let mut r = StreamingResampler::new(from_rate).unwrap();
|
|
|
|
// Push in irregular chunks to exercise the residual buffer.
|
|
let mut produced: Vec<f32> = Vec::new();
|
|
for window in samples.chunks(700) {
|
|
produced.extend(r.push_samples(window).unwrap());
|
|
}
|
|
produced.extend(r.flush().unwrap());
|
|
|
|
let out_secs = produced.len() as f64 / WHISPER_SAMPLE_RATE as f64;
|
|
assert!(
|
|
(out_secs - secs).abs() < 0.05,
|
|
"expected ~{secs}s of 16 kHz output, got {out_secs}s ({} samples)",
|
|
produced.len(),
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn flush_after_no_input_is_empty() {
|
|
let mut r = StreamingResampler::new(48_000).unwrap();
|
|
assert!(r.flush().unwrap().is_empty());
|
|
}
|
|
}
|