Struct FileAnalyzer 

pub struct FileAnalyzer<'model, 'a> { /* private fields */ }

Analyzes complete mono audio buffers.

FileAnalyzer is a convenience wrapper around a Collector and Analyzer pair for non-real-time analysis of audio that is already loaded in memory.

Each call to analyze configures the collector for mono input with the model’s optimal frame size. It analyzes independent five-second windows, advancing the start of each window by step_samples.

For streaming or multi-channel analysis, use analyzer_pair directly.

Implementations

impl<'model, 'a> FileAnalyzer<'model, 'a>

pub fn new( model: &'model Model<'a>, license_key: &str, ) -> Result<Self, AicError>

Creates a new file analyzer.

The collector is not initialized until analyze is called. This lets the same FileAnalyzer instance analyze mono buffers with different sample rates or step sizes.

Arguments

• model - The loaded model instance
• license_key - license key for the ai-coustics SDK (generate your key at developers.ai-coustics.com)

Returns

Returns a FileAnalyzer if the analyzer pair can be created, otherwise an AicError.

Example

let mut analyzer = FileAnalyzer::new(&model, &license_key)?;

let sample_rate = 16_000;
let audio = vec![0.0f32; 8000];
let results = analyzer.analyze(&audio, sample_rate, None)?;

pub fn analyze( &mut self, audio: &[f32], sample_rate: u32, step_samples: Option<usize>, ) -> Result<Vec<AnalysisResult>, AicError>

Analyzes a complete mono audio buffer.

The input slice must contain mono f32 samples at sample_rate. No channel mixing or resampling is performed.

The analyzer evaluates five-second windows. FileAnalyzer buffers a window starting at sample 0, runs the analyzer once, resets the analyzer and collector, then repeats with a window starting step_samples later.

If audio is shorter than or equal to five seconds, it is padded with silence and only one result is returned. For longer signals, only complete five-second windows are analyzed after the first window.

Arguments

• audio - Mono audio samples to analyze
• sample_rate - Sample rate of audio in Hz
• step_samples - Number of samples to advance between analysis results. Defaults to the model’s window size (no overlap in analysis windows) if None.

Returns

Returns a list of AnalysisResult values, or an AicError if initialization, buffering, or analysis fails.

Real-time safety

This function is not real-time safe. Avoid calling it from audio threads.