Skip to main content

VqCodebook

Struct VqCodebook 

Source
pub struct VqCodebook<B: Backend> { /* private fields */ }
Expand description

VQ Semantic Codebook for dequantizing semantic token indices.

Uses EMA (Exponential Moving Average) codebook: the embedding for each entry is embedding_sum / cluster_usage. This normalizes accumulated embeddings by how often each codebook entry was used during training.

Pre-normalizes embeddings to CPU cache at construction to avoid GPU readback during dequantize() (required for WASM compatibility).

Implementations§

Source§

impl<B: Backend> VqCodebook<B>

Source

pub fn new( embedding_sum: Tensor<B, 2>, cluster_usage: Tensor<B, 1>, cpu_normalized: Vec<f32>, ) -> Self

Create VQ codebook from loaded tensors and pre-computed CPU cache.

Use Self::precompute_normalized to build the CPU cache from raw f32 slices (before uploading to GPU) to avoid GPU readback.

Source

pub fn precompute_normalized( embed_vals: &[f32], usage_vals: &[f32], n_entries: usize, embed_dim: usize, ) -> Vec<f32>

Pre-compute normalized embeddings from raw f32 slices.

Call this on CPU-side data BEFORE constructing tensors, to avoid any GPU readback (required for WASM compatibility).

Source

pub fn from_safetensors( safetensors: &SafeTensors<'_>, device: &B::Device, ) -> Result<Self>

Load VQ codebook from SafeTensors.

Expects:

  • audio_tokenizer.quantizer.semantic_codebook.embedding_sum [8192, 256]
  • audio_tokenizer.quantizer.semantic_codebook.cluster_usage [8192]
Source

pub fn dequantize(&self, indices: &[usize]) -> Tensor<B, 2>

Dequantize a batch of semantic token indices to embedding vectors.

§Arguments
  • indices - Semantic token indices, each in [0, 8191]. Shape: [N]
§Returns

Embedding vectors [N, 256], normalized by cluster usage.

Source

pub fn dequantize_one(&self, index: usize) -> Tensor<B, 2>

Dequantize a single semantic token index.

§Arguments
  • index - Semantic token index in [0, 8191]
§Returns

Embedding vector [1, 256], normalized by cluster usage.

Trait Implementations§

Source§

impl<B> AutodiffModule<B> for VqCodebook<B>

Source§

type InnerModule = VqCodebook<<B as AutodiffBackend>::InnerBackend>

Inner module without auto-differentiation.
Source§

fn valid(&self) -> Self::InnerModule

Get the same module, but on the inner backend without auto-differentiation.
Source§

impl<B: Backend> Clone for VqCodebook<B>

Source§

fn clone(&self) -> Self

Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§

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

Performs copy-assignment from source. Read more
Source§

impl<B: Debug + Backend> Debug for VqCodebook<B>

Source§

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

Formats the value using the given formatter. Read more
Source§

impl<B: Backend> Display for VqCodebook<B>

Source§

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

Formats the value using the given formatter. Read more
Source§

impl<B: Backend> Module<B> for VqCodebook<B>

Source§

type Record = VqCodebookRecord<B>

Type to save and load the module.
Source§

fn load_record(self, record: Self::Record) -> Self

Load the module state from a record.
Source§

fn into_record(self) -> Self::Record

Convert the module into a record containing the state.
Source§

fn num_params(&self) -> usize

Get the number of parameters the module has, including all of its sub-modules.
Source§

fn visit<Visitor: ModuleVisitor<B>>(&self, visitor: &mut Visitor)

Visit each tensor parameter in the module with a visitor.
Source§

fn map<Mapper: ModuleMapper<B>>(self, mapper: &mut Mapper) -> Self

Map each tensor parameter in the module with a mapper.
Source§

fn collect_devices(&self, devices: Devices<B>) -> Devices<B>

Return all the devices found in the underneath module tree added to the given vector without duplicates.
Source§

fn to_device(self, device: &B::Device) -> Self

Move the module and all of its sub-modules to the given device. Read more
Source§

fn fork(self, device: &B::Device) -> Self

Fork the module and all of its sub-modules to the given device. Read more
Source§

fn devices(&self) -> Vec<<B as Backend>::Device>

Return all the devices found in the underneath module tree without duplicates.
Source§

fn no_grad(self) -> Self

Each tensor in the module tree will not require grad. Read more
Source§

fn save_file<FR, PB>( self, file_path: PB, recorder: &FR, ) -> Result<(), RecorderError>
where FR: FileRecorder<B>, PB: Into<PathBuf>,

Save the module to a file using the provided file recorder. Read more
Source§

fn load_file<FR, PB>( self, file_path: PB, recorder: &FR, device: &<B as Backend>::Device, ) -> Result<Self, RecorderError>
where FR: FileRecorder<B>, PB: Into<PathBuf>,

Load the module from a file using the provided file recorder. Read more
Source§

fn quantize_weights(self, quantizer: &mut Quantizer) -> Self

Quantize the weights of the module.
Source§

impl<B: Backend> ModuleDisplay for VqCodebook<B>

Source§

fn format(&self, passed_settings: DisplaySettings) -> String

Formats the module with provided display settings. Read more
Source§

fn custom_settings(&self) -> Option<DisplaySettings>

Custom display settings for the module. Read more
Source§

fn custom_content(&self, _content: Content) -> Option<Content>

Custom attributes for the module. Read more
Source§

impl<B: Backend> ModuleDisplayDefault for VqCodebook<B>

Source§

fn content(&self, content: Content) -> Option<Content>

Attributes of the module used for display purposes. Read more
Source§

fn num_params(&self) -> usize

Gets the number of the parameters of the module.

Auto Trait Implementations§

§

impl<B> !Freeze for VqCodebook<B>

§

impl<B> !RefUnwindSafe for VqCodebook<B>

§

impl<B> !Sync for VqCodebook<B>

§

impl<B> !UnwindSafe for VqCodebook<B>

§

impl<B> Send for VqCodebook<B>
where Param<Tensor<B, 2>>: Send, Param<Tensor<B, 1>>: Send,

§

impl<B> Unpin for VqCodebook<B>
where Param<Tensor<B, 2>>: Unpin, Param<Tensor<B, 1>>: Unpin,

§

impl<B> UnsafeUnpin for VqCodebook<B>

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§

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

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

impl<T> Downcast<T> for T

Source§

fn downcast(&self) -> &T

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> IntoComptime for T

Source§

fn comptime(self) -> Self

Source§

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

Source§

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> ToString for T
where T: Display + ?Sized,

Source§

fn to_string(&self) -> String

Converts the given value to a String. Read more
Source§

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

Source§

type Error = !

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

fn try_from(value: U) -> Result<T, !>

Performs the conversion.
Source§

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

Source§

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> Upcast<T> for T

Source§

fn upcast(&self) -> Option<&T>

Source§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

Source§

fn vzip(self) -> V

Source§

impl<T> WasmNotSend for T
where T: Send,

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