### Setup Sherpa-onnx with Static Linking

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/index.html

Add this to your Cargo.toml to use the sherpa-onnx crate with its default static linking. The build script will automatically download prebuilt libraries if SHERPA_ONNX_LIB_DIR is not set.

```toml
sherpa-onnx = "1.13.2"
```

--------------------------------

### Setup Sherpa-onnx with Shared Libraries

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/index.html

To use shared libraries instead of static ones, disable the default features and enable the 'shared' feature in your Cargo.toml.

```toml
sherpa-onnx = { version = "1.13.2", default-features = false, features = ["shared"] }
```

--------------------------------

### Create and Use OfflineRecognizer

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineRecognizer.html

Demonstrates how to create an OfflineRecognizer, configure it with model paths, create a stream, accept audio data, and decode it to get the recognized text. Ensure all model files are correctly specified.

```rust
use sherpa_onnx::{
    OfflineRecognizer,
    OfflineRecognizerConfig,
    OfflineTransducerModelConfig,
    Wave,
};

let wave = Wave::read("./test.wav").expect("read wave");
let mut config = OfflineRecognizerConfig::default();
config.model_config.transducer = OfflineTransducerModelConfig {
    encoder: Some("./sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8/encoder.int8.onnx".into()),
    decoder: Some("./sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8/decoder.int8.onnx".into()),
    joiner: Some("./sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8/joiner.int8.onnx".into()),
};
config.model_config.tokens =
    Some("./sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8/tokens.txt".into());
config.model_config.model_type = Some("nemo_transducer".into());

let recognizer = OfflineRecognizer::create(&config).expect("create recognizer");
let stream = recognizer.create_stream();
stream.accept_waveform(wave.sample_rate(), wave.samples());
recognizer.decode(&stream);
let result = stream.get_result().expect("result");
println!("{}", result.text);
```

--------------------------------

### Set SHERPA_ONNX_LIB_DIR for Advanced Setup

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/index.html

For advanced use cases, you can specify the directory containing sherpa-onnx libraries by setting the SHERPA_ONNX_LIB_DIR environment variable. This works for both static and shared builds.

```shell
export SHERPA_ONNX_LIB_DIR=/path/to/sherpa-onnx/lib
```

--------------------------------

### Offline ASR with SenseVoice Model

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/index.html

This example demonstrates how to perform offline Automatic Speech Recognition using the SenseVoice model. It involves reading a WAV file, configuring the recognizer with model paths and language settings, and decoding the audio stream.

```rust
use sherpa_onnx::{
    OfflineRecognizer,
    OfflineRecognizerConfig,
    OfflineSenseVoiceModelConfig,
    Wave,
};

let wave = Wave::read("./test.wav").expect("read wave");

let mut config = OfflineRecognizerConfig::default();
config.model_config.sense_voice = OfflineSenseVoiceModelConfig {
    model: Some(
        "./sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17-int8/model.int8.onnx".into(),
    ),
    language: Some("auto".into()),
    use_itn: true,
};
config.model_config.tokens = Some(
    "./sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17-int8/tokens.txt".into(),
);

let recognizer = OfflineRecognizer::create(&config).expect("create recognizer");
let stream = recognizer.create_stream();
stream.accept_waveform(wave.sample_rate(), wave.samples());
recognizer.decode(&stream);

let result = stream.get_result().expect("result");
println!("{}", result.text);
```

--------------------------------

### Get Samples from CircularBuffer

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.CircularBuffer.html

Copies a specified number of samples starting from a given index in the CircularBuffer.

```rust
pub fn get(&self, start_index: i32, n: i32) -> Vec<f32>
```

--------------------------------

### Get number of samples

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.Wave.html

Returns the total number of samples in the waveform.

```rust
pub fn num_samples(&self) -> i32
```

--------------------------------

### Default Implementation for OfflineTtsModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineTtsModelConfig.html

Provides a default configuration for OfflineTtsModelConfig. This is useful for creating a basic setup without manually specifying all parameters.

```rust
fn default() -> OfflineTtsModelConfig
```

--------------------------------

### Get Start Index of SpeechSegment

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpeechSegment.html

Retrieves the start index of the speech segment in samples, relative to the input processed so far.

```rust
pub fn start(&self) -> i32
```

--------------------------------

### CircularBuffer::get

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.CircularBuffer.html

Copies a specified number of samples starting from a given index in the CircularBuffer.

```APIDOC
## CircularBuffer::get

### Description
Copy `n` samples starting at `start_index`.

### Method
`get(&self, start_index: i32, n: i32) -> Vec<f32>`

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response (Vec<f32>)
- A `Vec<f32>` containing the copied samples.

#### Response Example
None
```

--------------------------------

### Get Stream Option

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineStream.html

Retrieves the string value associated with a given option key from the stream.

```rust
pub fn get_option(&self, key: &str) -> String
```

--------------------------------

### Default SileroVadModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SileroVadModelConfig.html

Provides the default configuration for the Silero VAD model. This is useful for quick setup when custom parameters are not immediately needed.

```rust
fn default() -> SileroVadModelConfig
```

--------------------------------

### Get Git Build Date

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/fn.git_date.html

Retrieves the Git date associated with the native library build. This can be useful for tracking build versions.

```rust
pub fn git_date() -> &'static str
```

--------------------------------

### Get Audio Sample Rate

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.GeneratedAudio.html

Return the output sample rate of the generated audio in Hz. This is crucial for correctly interpreting the audio data.

```rust
pub fn sample_rate(&self) -> i32
```

--------------------------------

### Get Segments Sorted by Start Time

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineSpeakerDiarizationResult.html

Returns a vector of all diarization segments, ordered chronologically by their start time.

```rust
pub fn sort_by_start_time(&self) -> Vec<OfflineSpeakerDiarizationSegment>
```

--------------------------------

### Create KeywordSpotter

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Creates a new KeywordSpotter instance from a given configuration. Returns None if creation fails.

```rust
pub fn create(config: &KeywordSpotterConfig) -> Option<Self>
```

--------------------------------

### Get sherpa-onnx Version

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/fn.version.html

Call the `version` function to retrieve the version string of the compiled sherpa-onnx native library. This function requires no arguments and returns a static string slice.

```rust
pub fn version() -> &'static str
```

--------------------------------

### KeywordSpotter::is_ready

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Checks if the provided online stream has accumulated enough audio data to perform the next decoding step.

```APIDOC
## KeywordSpotter::is_ready

### Description
Return `true` if `stream` has enough audio for another decode step.

### Method
```
pub fn is_ready(&self, stream: &OnlineStream) -> bool
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response
- **bool** - `true` if the stream is ready for decoding, `false` otherwise.

#### Response Example
None
```

--------------------------------

### KeywordSpotter::create

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Creates a new KeywordSpotter instance from a given configuration. Returns None if the configuration is invalid or the spotter cannot be created.

```APIDOC
## KeywordSpotter::create

### Description
Creates a keyword spotter from `KeywordSpotterConfig`.

### Method
```
pub fn create(config: &KeywordSpotterConfig) -> Option<Self>
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response
- **Self** (Option<KeywordSpotter>) - An optional KeywordSpotter instance.

#### Response Example
None
```

--------------------------------

### Get Embedding Dimension

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpeakerEmbeddingExtractor.html

Returns the dimension of the speaker embeddings that this extractor produces.

```rust
pub fn dim(&self) -> i32
```

--------------------------------

### Create AudioTagger Instance

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioTagging.html

Creates a new AudioTagging instance using the provided configuration. Returns None if creation fails.

```rust
pub fn create(config: &AudioTaggingConfig) -> Option<Self>
```

--------------------------------

### Get Number of Segments

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineSpeakerDiarizationResult.html

Retrieves the total count of diarization segments identified.

```rust
pub fn num_segments(&self) -> i32
```

--------------------------------

### Get All Speaker Names

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpeakerEmbeddingManager.html

Retrieves a list of all speaker names currently stored in the SpeakerEmbeddingManager.

```rust
pub fn get_all_speakers(&self) -> Vec<String>
```

--------------------------------

### DisplayManager::new

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.DisplayManager.html

Creates a new, empty instance of the DisplayManager.

```APIDOC
## DisplayManager::new

### Description
Creates an empty display manager.

### Method

```rust
pub fn new() -> Self
```

### Returns

A new instance of `DisplayManager`.
```

--------------------------------

### Get Logical Head Position of CircularBuffer

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.CircularBuffer.html

Returns the logical head position of the CircularBuffer.

```rust
pub fn head(&self) -> i32
```

--------------------------------

### Clone Implementation for KeywordSpotterConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotterConfig.html

Provides methods to create a duplicate of a KeywordSpotterConfig instance or perform copy-assignment.

```rust
fn clone(&self) -> KeywordSpotterConfig
```

```rust
fn clone_from(&mut self, source: &Self)
```

--------------------------------

### Get Current Size of CircularBuffer

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.CircularBuffer.html

Returns the current number of samples stored in the CircularBuffer.

```rust
pub fn size(&self) -> i32
```

--------------------------------

### Get Number of Samples in Segment

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpeechSegment.html

Returns the total number of samples present in the speech segment.

```rust
pub fn n(&self) -> i32
```

--------------------------------

### Create OnlineSpeechDenoiser Instance

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineSpeechDenoiser.html

Creates a new instance of OnlineSpeechDenoiser using the provided configuration. Returns None if creation fails.

```rust
pub fn create(config: &OnlineSpeechDenoiserConfig) -> Option<Self>
```

--------------------------------

### AudioTagging::create

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioTagging.html

Creates an offline audio tagger instance from the provided configuration. Returns None if the configuration is invalid or the tagger cannot be initialized.

```APIDOC
## AudioTagging::create

### Description
Creates a tagger from `config`.

### Method
```
pub fn create(config: &AudioTaggingConfig) -> Option<Self>
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response
- **Self** (AudioTagging) - An instance of the AudioTagging struct.

#### Response Example
None
```

--------------------------------

### Get Number of Speakers

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineSpeakerDiarizationResult.html

Retrieves the total number of unique speakers detected in the diarization result.

```rust
pub fn num_speakers(&self) -> i32
```

--------------------------------

### OnlinePunctuation::create

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlinePunctuation.html

Creates a new instance of OnlinePunctuation with the given configuration.

```APIDOC
## OnlinePunctuation::create

### Description
Creates a new instance of `OnlinePunctuation` with the given configuration.

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Method
```
pub fn create(config: &OnlinePunctuationConfig) -> Option<Self>
```

### Returns
An `Option<Self>` which is `Some(OnlinePunctuation)` on success, or `None` if creation fails.
```

--------------------------------

### Initialize and Use Streaming Recognizer

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/index.html

This snippet shows how to configure and use the `OnlineRecognizer` for streaming speech recognition. Ensure all model paths in the configuration are correct.

```rust
use sherpa_onnx::{OnlineRecognizer, OnlineRecognizerConfig, Wave};

let wave = Wave::read("./test.wav").expect("read wave");

let mut config = OnlineRecognizerConfig::default();
config.model_config.transducer.encoder = Some(
    "./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/encoder-epoch-99-avg-1.int8.onnx".into(),
);
config.model_config.transducer.decoder = Some(
    "./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/decoder-epoch-99-avg-1.onnx".into(),
);
config.model_config.transducer.joiner = Some(
    "./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/joiner-epoch-99-avg-1.int8.onnx".into(),
);
config.model_config.tokens = Some(
    "./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/tokens.txt".into(),
);
config.enable_endpoint = true;
config.decoding_method = Some("greedy_search".into());

let recognizer = OnlineRecognizer::create(&config).expect("create recognizer");
let stream = recognizer.create_stream();
stream.accept_waveform(wave.sample_rate(), wave.samples());
stream.input_finished();
while recognizer.is_ready(&stream) {
    recognizer.decode(&stream);
}
```

--------------------------------

### Get Output Sample Rate

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.LinearResampler.html

Retrieves the configured output sample rate of the resampler in Hz.

```rust
pub fn output_sample_rate(&self) -> i32
```

--------------------------------

### Get Input Sample Rate

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.LinearResampler.html

Retrieves the configured input sample rate of the resampler in Hz.

```rust
pub fn input_sample_rate(&self) -> i32
```

--------------------------------

### Get Recognition Result

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineRecognizer.html

Fetches the current recognition hypothesis for a given stream. Returns None if no result is available.

```rust
pub fn get_result(&self, stream: &OnlineStream) -> Option<RecognizerResult>
```

--------------------------------

### Clone Implementation for OfflineQwen3ASRModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineQwen3ASRModelConfig.html

Enables cloning an existing OfflineQwen3ASRModelConfig instance. This is useful for creating copies of configurations or for passing configurations by value.

```rust
fn clone(&self) -> OfflineQwen3ASRModelConfig
```

```rust
fn clone_from(&mut self, source: &Self)
```

--------------------------------

### OfflineStream::get_result

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineStream.html

Fetches the current recognition result from the stream. This method can be called periodically to get intermediate or final results.

```APIDOC
## OfflineStream::get_result

### Description
Fetch the current recognition result.

### Method
`get_result(&self) -> Option<OfflineRecognizerResult>`

### Returns
- `Option<OfflineRecognizerResult>` - An optional `OfflineRecognizerResult` containing the recognition result, or `None` if no result is available yet.
```

--------------------------------

### write

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/index.html

Writes normalized PCM samples to a WAV file.

```APIDOC
## write

### Description
Write normalized PCM samples to a WAV file.

### Parameters
#### Path Parameters
- **filename** (string) - Required - The name of the WAV file to write.
- **samples** (array of floats) - Required - The normalized PCM samples to write.
```

--------------------------------

### CloneToUninit (Nightly) Implementation

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioEvent.html

An experimental nightly feature that allows cloning an AudioEvent directly into uninitialized memory. Use with caution as it is unstable.

```rust
unsafe fn clone_to_uninit(&self, dest: *mut u8)
```

--------------------------------

### RecognizerResult Struct Definition

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.RecognizerResult.html

Defines the structure for ASR results, including text, tokens, timestamps, segment, start time, and finality.

```rust
pub struct RecognizerResult {
    pub text: String,
    pub tokens: Vec<String>,
    pub timestamps: Option<Vec<f32>>,
    pub segment: Option<i32>,
    pub start_time: Option<f32>,
    pub is_final: bool,
}
```

--------------------------------

### KeywordSpotter::create_stream_with_keywords

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Creates an online stream for this KeywordSpotter, specifically using a provided string of keywords, overriding any pre-configured list.

```APIDOC
## KeywordSpotter::create_stream_with_keywords

### Description
Creates a stream that uses `keywords` instead of the configured keyword list.

### Method
```
pub fn create_stream_with_keywords(&self, keywords: &str) -> OnlineStream
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response
- **OnlineStream** - An OnlineStream object configured with the specified keywords.

#### Response Example
None
```

--------------------------------

### OfflineSpeakerDiarizationSegment Struct Definition

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineSpeakerDiarizationSegment.html

Defines the structure for an offline speaker diarization segment, including start and end times, and the speaker index.

```rust
pub struct OfflineSpeakerDiarizationSegment {
    pub start: f32,
    pub end: f32,
    pub speaker: i32,
}
```

--------------------------------

### Get OnlineSpeechDenoiser Frame Shift

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineSpeechDenoiser.html

Returns the preferred input frame shift in samples, indicating the optimal chunk size for processing.

```rust
pub fn frame_shift_in_samples(&self) -> i32
```

--------------------------------

### OnlineRecognizer::create

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineRecognizer.html

Creates a new OnlineRecognizer instance from the provided configuration. Returns None if the configuration is invalid or the recognizer cannot be created.

```APIDOC
## OnlineRecognizer::create

### Description
Creates a recognizer from `config`.

### Method
```
pub fn create(config: &OnlineRecognizerConfig) -> Option<Self>
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response
- **Self** (Option<OnlineRecognizer>) - A new OnlineRecognizer instance or None.

#### Response Example
None
```

--------------------------------

### Get Keyword Spotting Result

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Retrieves the structured keyword spotting result for a given stream. Returns None if no result is available.

```rust
pub fn get_result(&self, stream: &OnlineStream) -> Option<KeywordResult>
```

--------------------------------

### Initialize and Use Offline TTS

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/index.html

This snippet demonstrates how to set up and use the `OfflineTts` for text-to-speech synthesis. Ensure all model paths within the `OfflineTtsConfig` are correctly specified.

```rust
use sherpa_onnx::{OfflineTts, OfflineTtsConfig, OfflineTtsModelConfig, OfflineTtsPocketModelConfig};

let config = OfflineTtsConfig {
    model: OfflineTtsModelConfig {
        pocket: OfflineTtsPocketModelConfig {
            lm_flow: Some("./sherpa-onnx-pocket-tts-int8-2026-01-26/lm_flow.int8.onnx".into()),
            lm_main: Some("./sherpa-onnx-pocket-tts-int8-2026-01-26/lm_main.int8.onnx".into()),
            encoder: Some("./sherpa-onnx-pocket-tts-int8-2026-01-26/encoder.onnx".into()),
            decoder: Some("./sherpa-onnx-pocket-tts-int8-2026-01-26/decoder.int8.onnx".into()),
            text_conditioner: Some(
                "./sherpa-onnx-pocket-tts-int8-2026-01-26/text_conditioner.onnx".into(),
            ),
            vocab_json: Some("./sherpa-onnx-pocket-tts-int8-2026-01-26/vocab.json".into()),
            token_scores_json: Some(
                "./sherpa-onnx-pocket-tts-int8-2026-01-26/token_scores.json".into(),
            ),
            ..Default::default()
        },
        ..Default::default()
    },
    ..Default::default()
};

let tts = OfflineTts::create(&config).expect("create tts");
println!("{}", tts.sample_rate());
```

--------------------------------

### Default Implementation for OnlineSpeechDenoiserConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineSpeechDenoiserConfig.html

Provides a default configuration for OnlineSpeechDenoiserConfig, allowing for easy initialization.

```rust
fn default() -> OnlineSpeechDenoiserConfig
```

--------------------------------

### From and Into Trait Implementations

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioTaggingModelConfig.html

Facilitates conversions to and from AudioTaggingModelConfig.

```rust
fn from(t: T) -> T
```

```rust
fn into(self) -> U
```

--------------------------------

### Create New DisplayManager

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.DisplayManager.html

Instantiates an empty DisplayManager. This is the constructor for the struct.

```rust
pub fn new() -> Self
```

--------------------------------

### Create Keyword Spotting Stream

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Creates a new online stream for keyword spotting using the keywords configured in the KeywordSpotterConfig.

```rust
pub fn create_stream(&self) -> OnlineStream
```

--------------------------------

### OfflineRecognizerConfig Struct Definition

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineRecognizerConfig.html

Defines the structure for configuring an offline speech recognizer. Use `Default` as a starting point and then customize fields for your specific model.

```rust
pub struct OfflineRecognizerConfig {
    pub feat_config: FeatureConfig,
    pub model_config: OfflineModelConfig,
    pub lm_config: OfflineLMConfig,
    pub decoding_method: Option<String>,
    pub max_active_paths: i32,
    pub hotwords_file: Option<String>,
    pub hotwords_score: f32,
    pub rule_fsts: Option<String>,
    pub rule_fars: Option<String>,
    pub blank_penalty: f32,
    pub hr: HomophoneReplacerConfig,
}
```

--------------------------------

### VoiceActivityDetector::create

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.VoiceActivityDetector.html

Creates a new VoiceActivityDetector instance with the specified configuration and buffer size. Returns None if initialization fails.

```APIDOC
## VoiceActivityDetector::create

### Description
Create a detector and an internal result buffer.

### Method Signature
`pub fn create(config: &VadModelConfig, buffer_size_in_seconds: f32) -> Option<Self>`

### Parameters
* `config` (*VadModelConfig*) - Configuration for the VAD model.
* `buffer_size_in_seconds` (*f32*) - The size of the internal buffer in seconds.
```

--------------------------------

### Get Result as JSON String

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Retrieves the keyword spotting result for a given stream formatted as a JSON string. Returns None if no result is available.

```rust
pub fn get_result_as_json(&self, stream: &OnlineStream) -> Option<String>
```

--------------------------------

### Clone Implementation for FastClusteringConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.FastClusteringConfig.html

Enables duplication of FastClusteringConfig instances. Use `clone()` to create a copy of an existing configuration.

```rust
fn clone(&self) -> FastClusteringConfig
```

--------------------------------

### Default Implementation for OnlinePunctuationConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlinePunctuationConfig.html

Provides a default value for OnlinePunctuationConfig, allowing for easy initialization.

```rust
fn default() -> OnlinePunctuationConfig
```

--------------------------------

### Get Top Speaker Matches

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpeakerEmbeddingManager.html

Retrieves up to 'n' best matching speaker names for a given embedding, provided they exceed the specified threshold. Returns a vector of SpeakerEmbeddingMatch.

```rust
pub fn get_best_matches(
    &self,
    embedding: &[f32],
    threshold: f32,
    n: i32,
) -> Vec<SpeakerEmbeddingMatch>
```

--------------------------------

### KeywordSpotter::create_stream

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Creates an online stream associated with this KeywordSpotter, using the keywords pre-configured in its KeywordSpotterConfig.

```APIDOC
## KeywordSpotter::create_stream

### Description
Creates a stream that uses the keywords configured in `KeywordSpotterConfig`.

### Method
```
pub fn create_stream(&self) -> OnlineStream
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response
- **OnlineStream** - An OnlineStream object configured with the spotter's keywords.

#### Response Example
None
```

--------------------------------

### Get Git SHA1 of Native Library Build

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/fn.git_sha1.html

Call this function to retrieve the Git SHA1 hash of the native library build. This can be useful for version checking or debugging.

```rust
pub fn git_sha1() -> &'static str
```

--------------------------------

### Create OnlineRecognizer

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineRecognizer.html

Creates a new OnlineRecognizer instance from a given configuration. Returns None if creation fails.

```rust
pub fn create(config: &OnlineRecognizerConfig) -> Option<Self>
```

--------------------------------

### Create Stream with Specific Keywords

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Creates a new online stream for keyword spotting using a custom set of keywords provided as a string.

```rust
pub fn create_stream_with_keywords(&self, keywords: &str) -> OnlineStream
```

--------------------------------

### version()

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/fn.version.html

Retrieves the version string of the compiled Sherpa-onnx native library.

```APIDOC
## version()

### Description
Returns the sherpa-onnx version string compiled into the native library.

### Function Signature
```rust
pub fn version() -> &'static str
```

### Returns
- `&'static str`: The Sherpa-onnx version string.
```

--------------------------------

### Default OnlineToneCtcModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineToneCtcModelConfig.html

Provides the default configuration for OnlineToneCtcModelConfig.

```rust
fn default() -> OnlineToneCtcModelConfig
```

--------------------------------

### Default Implementation for OfflineWenetCtcModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineWenetCtcModelConfig.html

Provides a default configuration for OfflineWenetCtcModelConfig.

```rust
fn default() -> OfflineWenetCtcModelConfig
```

--------------------------------

### Write PCM Samples to WAV File

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/fn.write.html

Use this function to directly write normalized PCM samples to a WAV file. It requires the output filename, a slice of f32 samples, and the audio sample rate.

```rust
pub fn write(filename: &str, samples: &[f32], sample_rate: i32) -> bool
```

--------------------------------

### KeywordSpotterConfig Struct Definition

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotterConfig.html

Defines the configuration structure for KeywordSpotter, including feature and model configurations, path limits, and keyword-specific settings.

```rust
pub struct KeywordSpotterConfig {
    pub feat_config: FeatureConfig,
    pub model_config: OnlineModelConfig,
    pub max_active_paths: i32,
    pub num_trailing_blanks: i32,
    pub keywords_score: f32,
    pub keywords_threshold: f32,
    pub keywords_file: Option<String>,
    pub keywords_buf: Option<String>,
}
```

--------------------------------

### Access Generated Audio Samples

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.GeneratedAudio.html

Borrow the generated audio samples as a slice of f32. This method is used to access the raw audio data.

```rust
pub fn samples(&self) -> &[f32]
```

--------------------------------

### LinearResampler::create

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.LinearResampler.html

Creates a new LinearResampler instance to convert audio from an input sample rate to an output sample rate.

```APIDOC
## LinearResampler::create

### Description
Creates a new resampler that converts from `samp_rate_in_hz` to `samp_rate_out_hz`.

### Method

```rust
pub fn create(samp_rate_in_hz: i32, samp_rate_out_hz: i32) -> Option<Self>
```

### Parameters

* `samp_rate_in_hz` (i32) - The input sample rate in Hz.
* `samp_rate_out_hz` (i32) - The output sample rate in Hz.

### Returns

An `Option<Self>` containing the new `LinearResampler` if successful, otherwise `None`.
```

--------------------------------

### Create Online Stream with Hotwords

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineRecognizer.html

Creates a new online stream that is pre-configured with specific hotwords for this stream only.

```rust
pub fn create_stream_with_hotwords(&self, hotwords: &str) -> OnlineStream
```

--------------------------------

### TryFrom and TryInto Trait Implementations

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioTaggingModelConfig.html

Enables fallible conversions to and from AudioTaggingModelConfig.

```rust
type Error = Infallible
```

```rust
fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>
```

```rust
fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>
```

--------------------------------

### Clone Implementation for OnlineSpeechDenoiserConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineSpeechDenoiserConfig.html

Provides methods to create a duplicate of an OnlineSpeechDenoiserConfig or copy assignment from another instance.

```rust
fn clone(&self) -> OnlineSpeechDenoiserConfig
```

```rust
fn clone_from(&mut self, source: &Self)
```

--------------------------------

### Clone Implementation for OfflineLMConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineLMConfig.html

Provides the ability to create a duplicate of an OfflineLMConfig instance. This is useful for copying configuration settings.

```rust
fn clone(&self) -> OfflineLMConfig
```

--------------------------------

### OfflineQwen3ASRModelConfig Struct Definition

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineQwen3ASRModelConfig.html

Defines the configuration parameters for an offline Qwen3 ASR model. This includes settings for the model's frontend, encoder, decoder, tokenizer, and various generation parameters like temperature and seed.

```rust
pub struct OfflineQwen3ASRModelConfig {
    pub conv_frontend: Option<String>,
    pub encoder: Option<String>,
    pub decoder: Option<String>,
    pub tokenizer: Option<String>,
    pub max_total_len: i32,
    pub max_new_tokens: i32,
    pub temperature: f32,
    pub top_p: f32,
    pub seed: i32,
    pub hotwords: Option<String>,
}
```

--------------------------------

### Default Implementation for AudioTaggingModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioTaggingModelConfig.html

Provides a default value for AudioTaggingModelConfig, useful for initialization.

```rust
fn default() -> Self
```

--------------------------------

### Create VoiceActivityDetector

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.VoiceActivityDetector.html

Creates a new VoiceActivityDetector instance with a specified model configuration and buffer size. Returns None if creation fails.

```rust
pub fn create( config: &VadModelConfig, buffer_size_in_seconds: f32, ) -> Option<Self>
```

--------------------------------

### Run OfflineSpeechDenoiser

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineSpeechDenoiser.html

Processes a chunk or a complete waveform of audio samples for denoising. Requires the audio samples and their sample rate.

```rust
pub fn run(&self, samples: &[f32], sample_rate: i32) -> DenoisedAudio
```

--------------------------------

### Default Implementation for OnlineTransducerModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineTransducerModelConfig.html

Provides a default configuration for OnlineTransducerModelConfig. This is useful for initializing the struct with sensible defaults.

```rust
fn default() -> OnlineTransducerModelConfig
```

--------------------------------

### Clone Implementation for OfflineWenetCtcModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineWenetCtcModelConfig.html

Provides methods to create a duplicate of the configuration or perform copy-assignment.

```rust
fn clone(&self) -> OfflineWenetCtcModelConfig
```

```rust
fn clone_from(&mut self, source: &Self)
```

--------------------------------

### Clone OnlineToneCtcModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineToneCtcModelConfig.html

Enables creating a duplicate of an OnlineToneCtcModelConfig instance.

```rust
fn clone(&self) -> OnlineToneCtcModelConfig
```

--------------------------------

### OnlineRecognizer::is_ready

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineRecognizer.html

Determines if the recognizer has received enough audio data to perform another recognition step.

```APIDOC
## OnlineRecognizer::is_ready

### Description
Return `true` if the recognizer has enough audio to run another step.

### Method
```
pub fn is_ready(&self, stream: &OnlineStream) -> bool
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response
- **bool** - `true` if the recognizer is ready for another step, `false` otherwise.

#### Response Example
None
```

--------------------------------

### write

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/fn.write.html

Writes normalized PCM samples to a WAV file. This function is useful for directly saving audio data without needing to construct a `Wave` object first.

```APIDOC
## write

### Description
Write normalized PCM samples to a WAV file. This is convenient when an API returns a plain `Vec<f32>` and you do not need to build a `Wave` first.

### Signature
```rust
pub fn write(filename: &str, samples: &[f32], sample_rate: i32) -> bool
```

### Parameters
* **filename** (`&str`): The name of the WAV file to write.
* **samples** (`&[f32]`): A slice of normalized PCM samples.
* **sample_rate** (`i32`): The sample rate of the audio data.

### Returns
* `bool`: Returns `true` if the samples were written successfully, `false` otherwise.
```

--------------------------------

### Default Implementation for OfflineFireRedAsrModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineFireRedAsrModelConfig.html

Provides a default configuration for OfflineFireRedAsrModelConfig, allowing for easy initialization.

```rust
fn default() -> OfflineFireRedAsrModelConfig
```

--------------------------------

### GeneratedAudio PinDrop Implementation (Nightly)

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.GeneratedAudio.html

Executes the destructor for the GeneratedAudio type requiring the instance to be pinned. This is an experimental, nightly-only API.

```rust
fn pin_drop(self: Pin<&mut Self>)
```

--------------------------------

### Create LinearResampler

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.LinearResampler.html

Creates a new LinearResampler instance. Specify the input and output sample rates in Hz. Returns None if the sample rates are invalid.

```rust
pub fn create(samp_rate_in_hz: i32, samp_rate_out_hz: i32) -> Option<Self>
```

--------------------------------

### Clone Implementation for AudioTaggingConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioTaggingConfig.html

Provides methods to create a duplicate of an AudioTaggingConfig value or perform copy-assignment.

```rust
fn clone(&self) -> AudioTaggingConfig
```

```rust
fn clone_from(&mut self, source: &Self)
```

--------------------------------

### Default Implementation for OnlineNemoCtcModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineNemoCtcModelConfig.html

Provides a default configuration for OnlineNemoCtcModelConfig.

```rust
fn default() -> OnlineNemoCtcModelConfig
```

--------------------------------

### Default Implementation for OnlineZipformer2CtcModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineZipformer2CtcModelConfig.html

Provides a default configuration for OnlineZipformer2CtcModelConfig. Use this when no specific configuration is needed.

```rust
fn default() -> OnlineZipformer2CtcModelConfig
```

--------------------------------

### Clone Implementation for OnlineRecognizerConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineRecognizerConfig.html

Provides methods to duplicate an OnlineRecognizerConfig instance. This is useful for creating independent configurations.

```rust
fn clone(&self) -> OnlineRecognizerConfig
```

```rust
fn clone_from(&mut self, source: &Self)
```

--------------------------------

### Create SpokenLanguageIdentification Instance

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpokenLanguageIdentification.html

Creates a language identifier instance using the provided configuration. Returns None if creation fails.

```rust
pub fn create(config: &SpokenLanguageIdentificationConfig) -> Option<Self>
```

--------------------------------

### Create SpeakerEmbeddingExtractor

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpeakerEmbeddingExtractor.html

Creates a new SpeakerEmbeddingExtractor instance from a given configuration. Returns None if creation fails.

```rust
pub fn create(config: &SpeakerEmbeddingExtractorConfig) -> Option<Self>
```

--------------------------------

### CloneToUninit Trait Implementation

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineTdnnModelConfig.html

Nightly-only experimental API for performing copy-assignment to uninitialized memory.

```rust
unsafe fn clone_to_uninit(&self, dest: *mut u8)

```

--------------------------------

### Clone Implementation for AudioTaggingModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioTaggingModelConfig.html

Provides methods to duplicate and copy-assign AudioTaggingModelConfig values.

```rust
fn clone(&self) -> AudioTaggingModelConfig
```

```rust
fn clone_from(&mut self, source: &Self)
```

--------------------------------

### Clone Implementation for OnlinePunctuationModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlinePunctuationModelConfig.html

Enables creating a duplicate of an existing OnlinePunctuationModelConfig instance. This is useful for modifying configurations without affecting the original.

```rust
fn clone(&self) -> OnlinePunctuationModelConfig
```

--------------------------------

### AudioTaggingConfig Struct Definition

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioTaggingConfig.html

Defines the top-level configuration for audio tagging, including model, labels, and top-k parameters.

```rust
pub struct AudioTaggingConfig {
    pub model: AudioTaggingModelConfig,
    pub labels: Option<String>,
    pub top_k: i32,
}
```

--------------------------------

### OnlineSpeechDenoiser Methods

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineSpeechDenoiser.html

Provides methods for interacting with the OnlineSpeechDenoiser, including creation, processing audio chunks, flushing remaining data, resetting state, and retrieving model parameters.

```APIDOC
## OnlineSpeechDenoiser

Streaming speech denoiser.

### `create(config: &OnlineSpeechDenoiserConfig) -> Option<Self>`

**Description**: Creates a new instance of `OnlineSpeechDenoiser` based on the provided configuration.

**Method**: `create`

**Parameters**:
* `config` (&OnlineSpeechDenoiserConfig) - Required - The configuration for the denoiser.

**Returns**: An `Option<Self>` which is `Some(OnlineSpeechDenoiser)` if creation is successful, `None` otherwise.

### `run(&self, samples: &[f32], sample_rate: i32) -> DenoisedAudio`

**Description**: Processes an input chunk of audio samples to denoise them.

**Method**: `run`

**Parameters**:
* `samples` (&[f32]) - Required - A slice of f32 representing the audio samples.
* `sample_rate` (i32) - Required - The sample rate of the input audio.

**Returns**: A `DenoisedAudio` struct containing the denoised audio data.

### `flush(&self) -> DenoisedAudio`

**Description**: Flushes any internally buffered samples after the final audio chunk has been processed.

**Method**: `flush`

**Returns**: A `DenoisedAudio` struct containing any remaining denoised audio data.

### `reset(&self)`

**Description**: Resets the internal streaming state of the denoiser.

**Method**: `reset`

### `sample_rate(&self) -> i32`

**Description**: Returns the sample rate that the denoiser model expects.

**Method**: `sample_rate`

**Returns**: An i32 representing the model's sample rate.

### `frame_shift_in_samples(&self) -> i32`

**Description**: Returns the preferred input frame shift in samples.

**Method**: `frame_shift_in_samples`

**Returns**: An i32 representing the preferred frame shift in samples.
```

--------------------------------

### Clone Implementation for OnlineModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineModelConfig.html

Enables creating a deep copy of an existing OnlineModelConfig instance.

```rust
fn clone(&self) -> OnlineModelConfig
```

```rust
fn clone_from(&mut self, source: &Self)
```

--------------------------------

### Wave::samples

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.Wave.html

Provides access to the normalized PCM samples of the waveform.

```APIDOC
## Wave::samples

### Description
Return the normalized PCM samples.

### Method
`pub fn samples(&self) -> &[f32]`

### Response
#### Success Response
- **&[f32]** - A slice containing the normalized f32 PCM samples.
```

--------------------------------

### Accept Waveform Samples

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.AudioTaggingOfflineStream.html

Appends waveform samples to the audio tagging stream. This method is part of the AudioTaggingOfflineStream's implementation.

```rust
pub fn accept_waveform(&self, sample_rate: i32, samples: &[f32])
```

--------------------------------

### SpeakerEmbeddingExtractor::create

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpeakerEmbeddingExtractor.html

Creates a new SpeakerEmbeddingExtractor instance from the provided configuration. Returns None if the configuration is invalid.

```APIDOC
## SpeakerEmbeddingExtractor::create

### Description
Create an extractor from `config`.

### Method
```
pub fn create(config: &SpeakerEmbeddingExtractorConfig) -> Option<Self>
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response
- **Self** (SpeakerEmbeddingExtractor) - An instance of SpeakerEmbeddingExtractor if creation is successful.

#### Response Example
```json
{
  "example": "Some(SpeakerEmbeddingExtractor { ... })"
}
```
```

--------------------------------

### KeywordSpotter::decode

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Performs one incremental decoding step for the given online stream.

```APIDOC
## KeywordSpotter::decode

### Description
Decode one incremental step for `stream`.

### Method
```
pub fn decode(&self, stream: &OnlineStream)
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response
None

#### Response Example
None
```

--------------------------------

### OfflineTts::generate_with_config

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineTts.html

Generates audio for the given text using the specified configuration and an optional callback for progress updates.

```APIDOC
## OfflineTts::generate_with_config

### Description
Generate audio for `text`. The optional callback receives the samples generated so far together with a progress value in `[0, 1]`. Return `true` to continue and `false` to stop early.

### Method
`pub fn generate_with_config<F>( &self, text: &str, config: &GenerationConfig, callback: Option<F>, ) -> Option<GeneratedAudio>
where F: FnMut(&[f32], f32) -> bool + 'static`

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
* **text** (`&str`) - Required - The text to synthesize.
* **config** (`&GenerationConfig`) - Required - Configuration for audio generation.
* **callback** (`Option<F>`) - Optional - A closure that receives generated audio samples and progress.

### Request Example
```rust
// Assuming GenerationConfig and GeneratedAudio are defined elsewhere
// let generation_config = GenerationConfig { ... };
// let callback = |samples: &[f32], progress: f32| -> bool {
//     println!("Progress: {:.2}", progress);
//     true // Continue generation
// };
// let audio_result = tts.generate_with_config("Hello world", &generation_config, Some(callback));
```

### Response
#### Success Response (Option<GeneratedAudio>)
* **GeneratedAudio** - An object containing the generated audio data and sample rate.

#### Response Example
`Some(GeneratedAudio { samples: vec![...], sample_rate: 48000 })` or `None`
```

--------------------------------

### Check Stream Readiness for Decoding

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordSpotter.html

Determines if the provided stream has accumulated enough audio data to perform another decoding step.

```rust
pub fn is_ready(&self, stream: &OnlineStream) -> bool
```

--------------------------------

### Clone Implementation for OfflineZipformerAudioTaggingModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineZipformerAudioTaggingModelConfig.html

Provides methods to create a duplicate of the configuration or perform copy-assignment.

```rust
fn clone(&self) -> OfflineZipformerAudioTaggingModelConfig
```

```rust
fn clone_from(&mut self, source: &Self)
```

--------------------------------

### Generic Implementations for OnlineRecognizerConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineRecognizerConfig.html

Shows various blanket implementations for traits like Send, Sync, and Any, indicating that OnlineRecognizerConfig can be safely shared across threads and used in generic contexts.

```rust
impl<T> Any for T
where T: 'static + ?Sized,
```

```rust
fn type_id(&self) -> TypeId
```

```rust
impl<T> Borrow<T> for T
where T: ?Sized,
```

```rust
fn borrow(&self) -> &T
```

```rust
impl<T> BorrowMut<T> for T
where T: ?Sized,
```

```rust
fn borrow_mut(&mut self) -> &mut T
```

```rust
impl<T> CloneToUninit for T
where T: Clone,
```

```rust
unsafe fn clone_to_uninit(&self, dest: *mut u8)
```

```rust
impl<T> From<T> for T
```

```rust
fn from(t: T) -> T
```

```rust
impl<T, U> Into<U> for T
where U: From<T>,
```

```rust
fn into(self) -> U
```

```rust
impl<T> ToOwned for T
where T: Clone,
```

```rust
type Owned = T
```

```rust
fn to_owned(&self) -> T
```

```rust
fn clone_into(&self, target: &mut T)
```

```rust
impl<T, U> TryFrom<U> for T
where U: Into<T>,
```

```rust
type Error = Infallible
```

```rust
fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>
```

```rust
impl<T, U> TryInto<U> for T
where U: TryFrom<T>,
```

```rust
type Error = <U as TryFrom<T>>::Error
```

```rust
fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>
```

--------------------------------

### file_exists

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/fn.file_exists.html

Checks if a file exists using the native file system helper. It takes a filename as input and returns a boolean indicating its existence.

```APIDOC
## file_exists

### Description
Returns `true` if `filename` exists according to the native helper.

### Signature
```rust
pub fn file_exists(filename: &str) -> bool
```

### Parameters
#### Path Parameters
- **filename** (str) - The name of the file to check for existence.
```

--------------------------------

### Create OfflineSpeechDenoiser

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineSpeechDenoiser.html

Creates an OfflineSpeechDenoiser instance from the provided configuration. Returns None if creation fails.

```rust
pub fn create(config: &OfflineSpeechDenoiserConfig) -> Option<Self>
```

--------------------------------

### Clone Implementation for OnlineTransducerModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlineTransducerModelConfig.html

Allows creating a duplicate of an OnlineTransducerModelConfig instance. This is useful when you need to modify a configuration without affecting the original.

```rust
fn clone(&self) -> OnlineTransducerModelConfig
```

--------------------------------

### Create OnlineStream for SpeakerEmbeddingExtractor

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpeakerEmbeddingExtractor.html

Creates an audio stream associated with the SpeakerEmbeddingExtractor. This stream can then be populated with audio data.

```rust
pub fn create_stream(&self) -> Option<OnlineStream>
```

--------------------------------

### Default Implementation for TenVadModelConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.TenVadModelConfig.html

Provides a default configuration for the TenVadModelConfig struct.

```rust
fn default() -> TenVadModelConfig
```

--------------------------------

### Generic CloneToUninit Implementation

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OfflineTtsKittenModelConfig.html

An experimental nightly-only API that allows cloning a value into uninitialized memory. Requires the type to implement the Clone trait.

```rust
unsafe fn clone_to_uninit(&self, dest: *mut u8)
Source
```

--------------------------------

### Default Implementation for SpokenLanguageIdentificationWhisperConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpokenLanguageIdentificationWhisperConfig.html

Provides a default configuration for SpokenLanguageIdentificationWhisperConfig. This is useful for initializing the struct with standard values.

```rust
fn default() -> SpokenLanguageIdentificationWhisperConfig
```

--------------------------------

### Clone Implementation for SpokenLanguageIdentificationWhisperConfig

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.SpokenLanguageIdentificationWhisperConfig.html

Enables creating a duplicate of an existing SpokenLanguageIdentificationWhisperConfig instance. This is useful for modifying configurations without affecting the original.

```rust
fn clone(&self) -> SpokenLanguageIdentificationWhisperConfig
```

--------------------------------

### OnlinePunctuationModelConfig Struct Definition

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.OnlinePunctuationModelConfig.html

Defines the configuration options for an online punctuation restoration model, including paths to CNN-BiLSTM and BPE vocabulary files, number of threads, debug flag, and provider.

```rust
pub struct OnlinePunctuationModelConfig {
    pub cnn_bilstm: Option<String>,
    pub bpe_vocab: Option<String>,
    pub num_threads: i32,
    pub debug: bool,
    pub provider: Option<String>,
}
```

--------------------------------

### Generic Blanket Implementations

Source: https://docs.rs/sherpa-onnx/latest/sherpa_onnx/struct.KeywordResult.html

Showcases various blanket implementations available for the KeywordResult struct, including Any, Borrow, CloneToUninit, From, Into, ToOwned, TryFrom, and TryInto.

```rust
fn type_id(&self) -> TypeId
```

```rust
fn borrow(&self) -> &T
```

```rust
fn borrow_mut(&mut self) -> &mut T
```

```rust
unsafe fn clone_to_uninit(&self, dest: *mut u8)
```

```rust
fn from(t: T) -> T
```

```rust
fn into(self) -> U
```

```rust
type Owned = T
```

```rust
fn to_owned(&self) -> T
```

```rust
fn clone_into(&self, target: &mut T)
```

```rust
type Error = Infallible
```

```rust
fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>
```

```rust
type Error = <U as TryFrom<T>>::Error
```

```rust
fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>
```