Skip to content

allow models without ivectors #20

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
al-zatv wants to merge 2 commits into
base: master
Choose a base branch
from
Open

allow models without ivectors #20

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6866bd6
If ivector_conf_filepath (conf/ivector_extractor.conf) is not found, …
al-zatv Jun 4, 2020
c0f8f79
explicit turning off ivector-related code
al-zatv Jun 11, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
69 changes: 38 additions & 31 deletions src/decoder.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -204,21 +204,26 @@ Decoder::~Decoder() noexcept {

void Decoder::start_decoding(const std::string &uuid) noexcept {
free_decoder();

adaptation_state_ = new kaldi::OnlineIvectorExtractorAdaptationState(model_->feature_info_->ivector_extractor_info);

feature_pipeline_ = new kaldi::OnlineNnet2FeaturePipeline(*model_->feature_info_);
feature_pipeline_->SetAdaptationState(*adaptation_state_);

if (model_->feature_info_->use_ivectors) {
adaptation_state_ = new kaldi::OnlineIvectorExtractorAdaptationState(model_->feature_info_->ivector_extractor_info);
feature_pipeline_->SetAdaptationState(*adaptation_state_);
silence_weighting_ = new kaldi::OnlineSilenceWeighting(model_->trans_model_,
model_->feature_info_->silence_weighting_config,
model_->decodable_opts_.frame_subsampling_factor);
}
else
{
adaptation_state_ = NULL;
silence_weighting_ = NULL;
}

decoder_ = new kaldi::SingleUtteranceNnet3Decoder(model_->lattice_faster_decoder_config_,
model_->trans_model_, *model_->decodable_info_,
*model_->decode_fst_, feature_pipeline_);
decoder_->InitDecoding();

silence_weighting_ = new kaldi::OnlineSilenceWeighting(model_->trans_model_,
model_->feature_info_->silence_weighting_config,
model_->decodable_opts_.frame_subsampling_factor);

uuid_ = uuid;
}

Expand Down Expand Up @@ -377,31 +382,33 @@ void Decoder::_decode_wave(kaldi::SubVector<kaldi::BaseFloat> &wave_part,

std::chrono::system_clock::time_point start_time;
if (DEBUG) start_time = std::chrono::system_clock::now();

if (silence_weighting_->Active() && feature_pipeline_->IvectorFeature() != NULL) {
silence_weighting_->ComputeCurrentTraceback(decoder_->Decoder());
silence_weighting_->GetDeltaWeights(feature_pipeline_->NumFramesReady(),
&delta_weights);

if (DEBUG) {
std::chrono::system_clock::time_point end_time = std::chrono::system_clock::now();
auto ms = std::chrono::duration_cast<std::chrono::milliseconds>(end_time - start_time);
std::cout << "[" << timestamp_now() << "] uuid: " << uuid_ << " silence weighting done in: " << ms.count() << "ms" << ENDL;

if (model_->feature_info_->use_ivectors) {
if (silence_weighting_->Active() && feature_pipeline_->IvectorFeature() != NULL) {
silence_weighting_->ComputeCurrentTraceback(decoder_->Decoder());
silence_weighting_->GetDeltaWeights(feature_pipeline_->NumFramesReady(),
&delta_weights);

if (DEBUG) {
std::chrono::system_clock::time_point end_time = std::chrono::system_clock::now();
auto ms = std::chrono::duration_cast<std::chrono::milliseconds>(end_time - start_time);
std::cout << "[" << timestamp_now() << "] uuid: " << uuid_ << " silence weighting done in: " << ms.count() << "ms" << ENDL;
}

if (DEBUG) start_time = std::chrono::system_clock::now();

feature_pipeline_->IvectorFeature()->UpdateFrameWeights(delta_weights);

if (DEBUG) {
std::chrono::system_clock::time_point end_time = std::chrono::system_clock::now();
auto ms = std::chrono::duration_cast<std::chrono::milliseconds>(end_time - start_time);
std::cout << "[" << timestamp_now() << "] uuid: " << uuid_ << " ivector frame weights updated in: " << ms.count() << "ms" << ENDL;
}

if (DEBUG) start_time = std::chrono::system_clock::now();
}

if (DEBUG) start_time = std::chrono::system_clock::now();

feature_pipeline_->IvectorFeature()->UpdateFrameWeights(delta_weights);

if (DEBUG) {
std::chrono::system_clock::time_point end_time = std::chrono::system_clock::now();
auto ms = std::chrono::duration_cast<std::chrono::milliseconds>(end_time - start_time);
std::cout << "[" << timestamp_now() << "] uuid: " << uuid_ << " ivector frame weights updated in: " << ms.count() << "ms" << ENDL;
}

if (DEBUG) start_time = std::chrono::system_clock::now();
}

decoder_->AdvanceDecoding();

if (DEBUG) {
Expand Down
39 changes: 24 additions & 15 deletions src/model.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,21 +147,30 @@ Model::Model(const ModelSpec &model_spec) : model_spec(model_spec) {
feature_info_->feature_type = "mfcc";
kaldi::ReadConfigFromFile(mfcc_conf_filepath, &(feature_info_->mfcc_opts));

feature_info_->use_ivectors = true;
kaldi::OnlineIvectorExtractionConfig ivector_extraction_opts;
kaldi::ReadConfigFromFile(ivector_conf_filepath, &ivector_extraction_opts);

// Expand paths if relative provided. We use model_dir as the base in
// such cases.
ivector_extraction_opts.lda_mat_rxfilename = expand_relative_path(ivector_extraction_opts.lda_mat_rxfilename, model_dir);
ivector_extraction_opts.global_cmvn_stats_rxfilename = expand_relative_path(ivector_extraction_opts.global_cmvn_stats_rxfilename, model_dir);
ivector_extraction_opts.diag_ubm_rxfilename = expand_relative_path(ivector_extraction_opts.diag_ubm_rxfilename, model_dir);
ivector_extraction_opts.ivector_extractor_rxfilename = expand_relative_path(ivector_extraction_opts.ivector_extractor_rxfilename, model_dir);
ivector_extraction_opts.cmvn_config_rxfilename = expand_relative_path(ivector_extraction_opts.cmvn_config_rxfilename, model_dir);
ivector_extraction_opts.splice_config_rxfilename = expand_relative_path(ivector_extraction_opts.splice_config_rxfilename, model_dir);

feature_info_->ivector_extractor_info.Init(ivector_extraction_opts);
feature_info_->silence_weighting_config.silence_weight = model_spec.silence_weight;
if (exists(ivector_conf_filepath))
{
feature_info_->use_ivectors = true;
kaldi::OnlineIvectorExtractionConfig ivector_extraction_opts;
kaldi::ReadConfigFromFile(ivector_conf_filepath, &ivector_extraction_opts);

// Expand paths if relative provided. We use model_dir as the base in
// such cases.
ivector_extraction_opts.lda_mat_rxfilename = expand_relative_path(ivector_extraction_opts.lda_mat_rxfilename, model_dir);
ivector_extraction_opts.global_cmvn_stats_rxfilename = expand_relative_path(ivector_extraction_opts.global_cmvn_stats_rxfilename, model_dir);
ivector_extraction_opts.diag_ubm_rxfilename = expand_relative_path(ivector_extraction_opts.diag_ubm_rxfilename, model_dir);
ivector_extraction_opts.ivector_extractor_rxfilename = expand_relative_path(ivector_extraction_opts.ivector_extractor_rxfilename, model_dir);
ivector_extraction_opts.cmvn_config_rxfilename = expand_relative_path(ivector_extraction_opts.cmvn_config_rxfilename, model_dir);
ivector_extraction_opts.splice_config_rxfilename = expand_relative_path(ivector_extraction_opts.splice_config_rxfilename, model_dir);

feature_info_->ivector_extractor_info.Init(ivector_extraction_opts);
feature_info_->silence_weighting_config.silence_weight = model_spec.silence_weight;
}
else
{
KALDI_WARN << ivector_conf_filepath << " file not found. Turning off ivectors.";
feature_info_->use_ivectors = false;
}


lattice_faster_decoder_config_.min_active = model_spec.min_active;
lattice_faster_decoder_config_.max_active = model_spec.max_active;
Expand Down