LSTM API

namespace lstm

Functions

LSTMConfig parse_config_json(const nlohmann::json &config)

Parse LSTM configuration from JSON.

Parameters:

config – JSON configuration object

Returns:

LSTMConfig

std::unique_ptr<ModelConfig> create_config(const nlohmann::json &config, double sampleRate)

Config parser for ConfigParserRegistry.

class LSTM : public nam::DSP
#include <lstm.h>

A multi-layer LSTM model.

A multi-layer LSTM processes audio frame-by-frame, maintaining hidden states across layers. Each layer processes the hidden state from the previous layer as input.

Public Functions

LSTM(const int in_channels, const int out_channels, const int num_layers, const int input_size, const int hidden_size, std::vector<float> &weights, const double expected_sample_rate = -1.0)

Constructor.

Parameters:

  • in_channels – Number of input channels

  • out_channels – Number of output channels

  • num_layers – Number of LSTM layers

  • input_size – Size of the input to each LSTM cell

  • hidden_size – Size of the hidden state in each LSTM cell

  • weights – Model weights vector

  • expected_sample_rate – Expected sample rate in Hz (-1.0 if unknown)

~LSTM() = default

Destructor.

virtual void process(NAM_SAMPLE **input, NAM_SAMPLE **output, const int num_frames) override

Process audio frames.

Parameters:

  • input – Input audio buffers

  • output – Output audio buffers

  • num_frames – Number of frames to process

virtual int GetPrewarmSamples() override

Get how many samples should be processed for the model to be considered “warmed up”.

Override this in subclasses to specify prewarm requirements.

Returns:

Number of samples needed for prewarm

void _process_sample()

Public Members

Eigen::MatrixXf _head_weight
Eigen::VectorXf _head_bias
std::vector<LSTMCell> _layers
Eigen::VectorXf _input
Eigen::VectorXf _output
class LSTMCell
#include <lstm.h>

A single LSTM cell.

Public Functions

LSTMCell(const int input_size, const int hidden_size, std::vector<float>::iterator &weights)

Constructor.

Parameters:

  • input_size – Size of the input vector

  • hidden_size – Size of the hidden state

  • weights – Iterator to the weights vector. Will be advanced as weights are consumed.

inline Eigen::VectorXf get_hidden_state() const

Get the current hidden state.

Returns:

Hidden state vector

void process_(const Eigen::VectorXf &x)

Process a single input vector.

Parameters:

x – Input vector

struct LSTMConfig : public nam::ModelConfig
#include <lstm.h>

Configuration for an LSTM model.

Public Functions

virtual std::unique_ptr<DSP> create(std::vector<float> weights, double sampleRate) override

Construct a DSP object from this configuration.

Parameters:

  • weights – Model weights (taken by value to allow move for WaveNet)

  • sampleRate – Expected sample rate in Hz

Returns:

Unique pointer to a DSP object

Public Members

int num_layers
int input_size
int hidden_size
int in_channels
int out_channels
class LSTM : public nam::DSP

A multi-layer LSTM model.

A multi-layer LSTM processes audio frame-by-frame, maintaining hidden states across layers. Each layer processes the hidden state from the previous layer as input.

Public Functions

LSTM(const int in_channels, const int out_channels, const int num_layers, const int input_size, const int hidden_size, std::vector<float> &weights, const double expected_sample_rate = -1.0)

Constructor.

Parameters:

  • in_channels – Number of input channels

  • out_channels – Number of output channels

  • num_layers – Number of LSTM layers

  • input_size – Size of the input to each LSTM cell

  • hidden_size – Size of the hidden state in each LSTM cell

  • weights – Model weights vector

  • expected_sample_rate – Expected sample rate in Hz (-1.0 if unknown)

~LSTM() = default

Destructor.

virtual void process(NAM_SAMPLE **input, NAM_SAMPLE **output, const int num_frames) override

Process audio frames.

Parameters:

  • input – Input audio buffers

  • output – Output audio buffers

  • num_frames – Number of frames to process

virtual int GetPrewarmSamples() override

Get how many samples should be processed for the model to be considered “warmed up”.

Override this in subclasses to specify prewarm requirements.

Returns:

Number of samples needed for prewarm

void _process_sample()

Public Members

Eigen::MatrixXf _head_weight
Eigen::VectorXf _head_bias
std::vector<LSTMCell> _layers
Eigen::VectorXf _input
Eigen::VectorXf _output
class LSTMCell

A single LSTM cell.

Public Functions

LSTMCell(const int input_size, const int hidden_size, std::vector<float>::iterator &weights)

Constructor.

Parameters:

  • input_size – Size of the input vector

  • hidden_size – Size of the hidden state

  • weights – Iterator to the weights vector. Will be advanced as weights are consumed.

inline Eigen::VectorXf get_hidden_state() const

Get the current hidden state.

Returns:

Hidden state vector

void process_(const Eigen::VectorXf &x)

Process a single input vector.

Parameters:

x – Input vector