Struct pyannote_rs::EmbeddingManager

source · 
pub struct EmbeddingManager { /* private fields */ }

Implementations§

source§

impl EmbeddingManager

source

pub fn new(max_speakers: usize) -> Self

Examples found in repository?
examples/infinite.rs (line 20)
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53

fn main() {
    let audio_path = std::env::args().nth(1).expect("Please specify audio file");
    let search_threshold = 0.5;

    let embedding_model_path = "wespeaker_en_voxceleb_CAM++.onnx";
    let segmentation_model_path = "segmentation-3.0.onnx";

    let (samples, sample_rate) = pyannote_rs::read_wav(&audio_path).unwrap();
    let mut embedding_extractor = EmbeddingExtractor::new(embedding_model_path).unwrap();
    let mut embedding_manager = EmbeddingManager::new(usize::MAX);

    let segments = pyannote_rs::segment(&samples, sample_rate, segmentation_model_path).unwrap();

    for segment in segments {
        // Compute the embedding result
        let embedding_result: Vec<f32> = match embedding_extractor.compute(&segment.samples) {
            Ok(result) => result.collect(),
            Err(error) => {
                println!(
                    "Error in {:.2}s: {:.2}s: {:?}",
                    segment.start, segment.end, error
                );
                println!(
                    "start = {:.2}, end = {:.2}, speaker = ?",
                    segment.start, segment.end
                );
                continue; // Skip to the next segment
            }
        };

        // Find the speaker
        let speaker = embedding_manager
            .search_speaker(embedding_result.clone(), search_threshold)
            .ok_or_else(|| embedding_manager.search_speaker(embedding_result, 0.0)) // Ensure always to return speaker
            .map(|r| r.to_string())
            .unwrap_or("?".into());

        println!(
            "start = {:.2}, end = {:.2}, speaker = {}",
            segment.start, segment.end, speaker
        );
    }
}
More examples
Hide additional examples
examples/max_speakers.rs (line 21)
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60

fn main() {
    let audio_path = std::env::args().nth(1).expect("Please specify audio file");
    let max_speakers = 6;
    let search_threshold = 0.5;

    let embedding_model_path = "wespeaker_en_voxceleb_CAM++.onnx";
    let segmentation_model_path = "segmentation-3.0.onnx";

    let (samples, sample_rate) = pyannote_rs::read_wav(&audio_path).unwrap();
    let mut embedding_extractor = EmbeddingExtractor::new(embedding_model_path).unwrap();
    let mut embedding_manager = EmbeddingManager::new(max_speakers);

    let segments = pyannote_rs::segment(&samples, sample_rate, segmentation_model_path).unwrap();

    for segment in segments {
        // Compute the embedding result
        let embedding_result = match embedding_extractor.compute(&segment.samples) {
            Ok(result) => result.collect(),
            Err(error) => {
                println!(
                    "Error in {:.2}s: {:.2}s: {:?}",
                    segment.start, segment.end, error
                );
                println!(
                    "start = {:.2}, end = {:.2}, speaker = ?",
                    segment.start, segment.end
                );
                continue; // Skip to the next segment
            }
        };

        // Find the speaker
        let speaker = if embedding_manager.get_all_speakers().len() == max_speakers {
            embedding_manager
                .get_best_speaker_match(embedding_result)
                .map(|r| r.to_string())
                .unwrap_or("?".into())
        } else {
            embedding_manager
                .search_speaker(embedding_result, search_threshold)
                .map(|r| r.to_string())
                .unwrap_or("?".into())
        };

        println!(
            "start = {:.2}, end = {:.2}, speaker = {}",
            segment.start, segment.end, speaker
        );
    }
}
source

pub fn search_speaker( &mut self, embedding: Vec<f32>, threshold: f32, ) -> Option<usize>

Search or create speaker

Examples found in repository?
examples/infinite.rs (line 43)
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53

fn main() {
    let audio_path = std::env::args().nth(1).expect("Please specify audio file");
    let search_threshold = 0.5;

    let embedding_model_path = "wespeaker_en_voxceleb_CAM++.onnx";
    let segmentation_model_path = "segmentation-3.0.onnx";

    let (samples, sample_rate) = pyannote_rs::read_wav(&audio_path).unwrap();
    let mut embedding_extractor = EmbeddingExtractor::new(embedding_model_path).unwrap();
    let mut embedding_manager = EmbeddingManager::new(usize::MAX);

    let segments = pyannote_rs::segment(&samples, sample_rate, segmentation_model_path).unwrap();

    for segment in segments {
        // Compute the embedding result
        let embedding_result: Vec<f32> = match embedding_extractor.compute(&segment.samples) {
            Ok(result) => result.collect(),
            Err(error) => {
                println!(
                    "Error in {:.2}s: {:.2}s: {:?}",
                    segment.start, segment.end, error
                );
                println!(
                    "start = {:.2}, end = {:.2}, speaker = ?",
                    segment.start, segment.end
                );
                continue; // Skip to the next segment
            }
        };

        // Find the speaker
        let speaker = embedding_manager
            .search_speaker(embedding_result.clone(), search_threshold)
            .ok_or_else(|| embedding_manager.search_speaker(embedding_result, 0.0)) // Ensure always to return speaker
            .map(|r| r.to_string())
            .unwrap_or("?".into());

        println!(
            "start = {:.2}, end = {:.2}, speaker = {}",
            segment.start, segment.end, speaker
        );
    }
}
More examples
Hide additional examples
examples/max_speakers.rs (line 50)
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60

fn main() {
    let audio_path = std::env::args().nth(1).expect("Please specify audio file");
    let max_speakers = 6;
    let search_threshold = 0.5;

    let embedding_model_path = "wespeaker_en_voxceleb_CAM++.onnx";
    let segmentation_model_path = "segmentation-3.0.onnx";

    let (samples, sample_rate) = pyannote_rs::read_wav(&audio_path).unwrap();
    let mut embedding_extractor = EmbeddingExtractor::new(embedding_model_path).unwrap();
    let mut embedding_manager = EmbeddingManager::new(max_speakers);

    let segments = pyannote_rs::segment(&samples, sample_rate, segmentation_model_path).unwrap();

    for segment in segments {
        // Compute the embedding result
        let embedding_result = match embedding_extractor.compute(&segment.samples) {
            Ok(result) => result.collect(),
            Err(error) => {
                println!(
                    "Error in {:.2}s: {:.2}s: {:?}",
                    segment.start, segment.end, error
                );
                println!(
                    "start = {:.2}, end = {:.2}, speaker = ?",
                    segment.start, segment.end
                );
                continue; // Skip to the next segment
            }
        };

        // Find the speaker
        let speaker = if embedding_manager.get_all_speakers().len() == max_speakers {
            embedding_manager
                .get_best_speaker_match(embedding_result)
                .map(|r| r.to_string())
                .unwrap_or("?".into())
        } else {
            embedding_manager
                .search_speaker(embedding_result, search_threshold)
                .map(|r| r.to_string())
                .unwrap_or("?".into())
        };

        println!(
            "start = {:.2}, end = {:.2}, speaker = {}",
            segment.start, segment.end, speaker
        );
    }
}
source

pub fn get_best_speaker_match(&mut self, embedding: Vec<f32>) -> Result<usize>

Examples found in repository?
examples/max_speakers.rs (line 45)
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60

fn main() {
    let audio_path = std::env::args().nth(1).expect("Please specify audio file");
    let max_speakers = 6;
    let search_threshold = 0.5;

    let embedding_model_path = "wespeaker_en_voxceleb_CAM++.onnx";
    let segmentation_model_path = "segmentation-3.0.onnx";

    let (samples, sample_rate) = pyannote_rs::read_wav(&audio_path).unwrap();
    let mut embedding_extractor = EmbeddingExtractor::new(embedding_model_path).unwrap();
    let mut embedding_manager = EmbeddingManager::new(max_speakers);

    let segments = pyannote_rs::segment(&samples, sample_rate, segmentation_model_path).unwrap();

    for segment in segments {
        // Compute the embedding result
        let embedding_result = match embedding_extractor.compute(&segment.samples) {
            Ok(result) => result.collect(),
            Err(error) => {
                println!(
                    "Error in {:.2}s: {:.2}s: {:?}",
                    segment.start, segment.end, error
                );
                println!(
                    "start = {:.2}, end = {:.2}, speaker = ?",
                    segment.start, segment.end
                );
                continue; // Skip to the next segment
            }
        };

        // Find the speaker
        let speaker = if embedding_manager.get_all_speakers().len() == max_speakers {
            embedding_manager
                .get_best_speaker_match(embedding_result)
                .map(|r| r.to_string())
                .unwrap_or("?".into())
        } else {
            embedding_manager
                .search_speaker(embedding_result, search_threshold)
                .map(|r| r.to_string())
                .unwrap_or("?".into())
        };

        println!(
            "start = {:.2}, end = {:.2}, speaker = {}",
            segment.start, segment.end, speaker
        );
    }
}
source

pub fn get_all_speakers(&self) -> &HashMap<usize, Array1<f32>>

Examples found in repository?
examples/max_speakers.rs (line 43)
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60

fn main() {
    let audio_path = std::env::args().nth(1).expect("Please specify audio file");
    let max_speakers = 6;
    let search_threshold = 0.5;

    let embedding_model_path = "wespeaker_en_voxceleb_CAM++.onnx";
    let segmentation_model_path = "segmentation-3.0.onnx";

    let (samples, sample_rate) = pyannote_rs::read_wav(&audio_path).unwrap();
    let mut embedding_extractor = EmbeddingExtractor::new(embedding_model_path).unwrap();
    let mut embedding_manager = EmbeddingManager::new(max_speakers);

    let segments = pyannote_rs::segment(&samples, sample_rate, segmentation_model_path).unwrap();

    for segment in segments {
        // Compute the embedding result
        let embedding_result = match embedding_extractor.compute(&segment.samples) {
            Ok(result) => result.collect(),
            Err(error) => {
                println!(
                    "Error in {:.2}s: {:.2}s: {:?}",
                    segment.start, segment.end, error
                );
                println!(
                    "start = {:.2}, end = {:.2}, speaker = ?",
                    segment.start, segment.end
                );
                continue; // Skip to the next segment
            }
        };

        // Find the speaker
        let speaker = if embedding_manager.get_all_speakers().len() == max_speakers {
            embedding_manager
                .get_best_speaker_match(embedding_result)
                .map(|r| r.to_string())
                .unwrap_or("?".into())
        } else {
            embedding_manager
                .search_speaker(embedding_result, search_threshold)
                .map(|r| r.to_string())
                .unwrap_or("?".into())
        };

        println!(
            "start = {:.2}, end = {:.2}, speaker = {}",
            segment.start, segment.end, speaker
        );
    }
}

Trait Implementations§

source§

impl Clone for EmbeddingManager

source§

fn clone(&self) -> EmbeddingManager

Returns a copy of the value. Read more
1.0.0 · source§

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

Performs copy-assignment from source. Read more
source§

impl Debug for EmbeddingManager

source§

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter. Read more

Auto Trait Implementations§

Blanket Implementations§

source§

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

source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
source§

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

source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
source§

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

source§

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

Mutably borrows from an owned value. Read more
source§

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

source§

default unsafe fn clone_to_uninit(&self, dst: *mut T)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dst. Read more
source§

impl<T> From<T> for T

source§

fn from(t: T) -> T

Returns the argument unchanged.

source§

impl<T> Instrument for T

source§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more
source§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
source§

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

source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

source§

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

§

type Owned = T

The resulting type after obtaining ownership.
source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
source§

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

Uses borrowed data to replace owned data, usually by cloning. Read more
source§

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

§

type Error = Infallible

The type returned in the event of a conversion error.
source§

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

Performs the conversion.
source§

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

§

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

The type returned in the event of a conversion error.
source§

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

Performs the conversion.
source§

impl<T> WithSubscriber for T

source§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more