Skip to content
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

treat unk as blank #299

Merged
merged 1 commit into from
Sep 7, 2023
Merged

treat unk as blank #299

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
21 changes: 15 additions & 6 deletions sherpa-onnx/csrc/online-recognizer-transducer-impl.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,17 +57,21 @@ class OnlineRecognizerTransducerImpl : public OnlineRecognizerImpl {
model_(OnlineTransducerModel::Create(config.model_config)),
sym_(config.model_config.tokens),
endpoint_(config_.endpoint_config) {
if (sym_.contains("<unk>")) {
unk_id_ = sym_["<unk>"];
}

if (config.decoding_method == "modified_beam_search") {
if (!config_.lm_config.model.empty()) {
lm_ = OnlineLM::Create(config.lm_config);
}

decoder_ = std::make_unique<OnlineTransducerModifiedBeamSearchDecoder>(
model_.get(), lm_.get(), config_.max_active_paths,
config_.lm_config.scale);
config_.lm_config.scale, unk_id_);
} else if (config.decoding_method == "greedy_search") {
decoder_ =
std::make_unique<OnlineTransducerGreedySearchDecoder>(model_.get());
decoder_ = std::make_unique<OnlineTransducerGreedySearchDecoder>(
model_.get(), unk_id_);
} else {
SHERPA_ONNX_LOGE("Unsupported decoding method: %s",
config.decoding_method.c_str());
Expand All @@ -82,13 +86,17 @@ class OnlineRecognizerTransducerImpl : public OnlineRecognizerImpl {
model_(OnlineTransducerModel::Create(mgr, config.model_config)),
sym_(mgr, config.model_config.tokens),
endpoint_(config_.endpoint_config) {
if (sym_.contains("<unk>")) {
unk_id_ = sym_["<unk>"];
}

if (config.decoding_method == "modified_beam_search") {
decoder_ = std::make_unique<OnlineTransducerModifiedBeamSearchDecoder>(
model_.get(), lm_.get(), config_.max_active_paths,
config_.lm_config.scale);
config_.lm_config.scale, unk_id_);
} else if (config.decoding_method == "greedy_search") {
decoder_ =
std::make_unique<OnlineTransducerGreedySearchDecoder>(model_.get());
decoder_ = std::make_unique<OnlineTransducerGreedySearchDecoder>(
model_.get(), unk_id_);
} else {
SHERPA_ONNX_LOGE("Unsupported decoding method: %s",
config.decoding_method.c_str());
Expand Down Expand Up @@ -268,6 +276,7 @@ class OnlineRecognizerTransducerImpl : public OnlineRecognizerImpl {
std::unique_ptr<OnlineTransducerDecoder> decoder_;
SymbolTable sym_;
Endpoint endpoint_;
int32_t unk_id_ = -1;
};

} // namespace sherpa_onnx
Expand Down
4 changes: 3 additions & 1 deletion sherpa-onnx/csrc/online-transducer-greedy-search-decoder.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,9 @@ void OnlineTransducerGreedySearchDecoder::Decode(
static_cast<const float *>(p_logit),
std::max_element(static_cast<const float *>(p_logit),
static_cast<const float *>(p_logit) + vocab_size)));
if (y != 0) {
// blank id is hardcoded to 0
// also, it treats unk as blank
if (y != 0 && y != unk_id_) {
emitted = true;
r.tokens.push_back(y);
r.timestamps.push_back(t + r.frame_offset);
Expand Down
6 changes: 4 additions & 2 deletions sherpa-onnx/csrc/online-transducer-greedy-search-decoder.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,9 @@ namespace sherpa_onnx {

class OnlineTransducerGreedySearchDecoder : public OnlineTransducerDecoder {
public:
explicit OnlineTransducerGreedySearchDecoder(OnlineTransducerModel *model)
: model_(model) {}
OnlineTransducerGreedySearchDecoder(OnlineTransducerModel *model,
int32_t unk_id)
: model_(model), unk_id_(unk_id) {}

OnlineTransducerDecoderResult GetEmptyResult() const override;

Expand All @@ -26,6 +27,7 @@ class OnlineTransducerGreedySearchDecoder : public OnlineTransducerDecoder {

private:
OnlineTransducerModel *model_; // Not owned
int32_t unk_id_;
};

} // namespace sherpa_onnx
Expand Down
4 changes: 3 additions & 1 deletion sherpa-onnx/csrc/online-transducer-modified-beam-search-decoder.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,7 +155,9 @@ void OnlineTransducerModifiedBeamSearchDecoder::Decode(
float context_score = 0;
auto context_state = new_hyp.context_state;

if (new_token != 0) {
// blank is hardcoded to 0
// also, it treats unk as blank
if (new_token != 0 && new_token != unk_id_) {
new_hyp.ys.push_back(new_token);
new_hyp.timestamps.push_back(t + frame_offset);
new_hyp.num_trailing_blanks = 0;
Expand Down
6 changes: 4 additions & 2 deletions sherpa-onnx/csrc/online-transducer-modified-beam-search-decoder.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,11 +21,12 @@ class OnlineTransducerModifiedBeamSearchDecoder
OnlineTransducerModifiedBeamSearchDecoder(OnlineTransducerModel *model,
OnlineLM *lm,
int32_t max_active_paths,
float lm_scale)
float lm_scale, int32_t unk_id)
: model_(model),
lm_(lm),
max_active_paths_(max_active_paths),
lm_scale_(lm_scale) {}
lm_scale_(lm_scale),
unk_id_(unk_id) {}

OnlineTransducerDecoderResult GetEmptyResult() const override;

Expand All @@ -45,6 +46,7 @@ class OnlineTransducerModifiedBeamSearchDecoder

int32_t max_active_paths_;
float lm_scale_; // used only when lm_ is not nullptr
int32_t unk_id_;
};

} // namespace sherpa_onnx
Expand Down
Loading