Skip to content

Fix language model repeated scoring #12

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
FieldsMedal wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix language model repeated scoring #12

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
23 changes: 11 additions & 12 deletions swig/ctc_beam_search_decoder.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,7 +137,8 @@ std::vector<std::pair<double, std::vector<int>>> ctc_beam_search_decoder(
float hotwords_score = 0.0;
std::vector<std::string> ngram;
PathTrie *prefix_to_score = nullptr;
if (hotwords_scorer != nullptr && !hotwords_scorer->hotwords_dict.empty()) {
if (hotwords_scorer != nullptr && !hotwords_scorer->hotwords_dict.empty() &&
(c == space_id || hotwords_scorer->is_character_based)) {
if (hotwords_scorer->is_character_based) {
prefix_to_score = prefix_new;
} else {
Expand All @@ -151,25 +152,23 @@ std::vector<std::pair<double, std::vector<int>>> ctc_beam_search_decoder(

// language model scoring
float ngram_score = 0.0;
if (ext_scorer != nullptr ) {
if (ext_scorer != nullptr && (c == space_id || ext_scorer->is_character_based())) {
if (hotwords_scorer != nullptr && !hotwords_scorer->hotwords_dict.empty() &&
!(hotwords_scorer->is_character_based ^ ext_scorer->is_character_based()) &&
hotwords_scorer->window_length >= ext_scorer->get_max_order()) {
std::vector<std::string>::const_iterator first = ngram.end() - ext_scorer->get_max_order();
std::vector<std::string>::const_iterator last = ngram.end();
std::vector<std::string> slice_ngram(first, last);
ngram_score = ext_scorer->get_log_cond_prob(slice_ngram) * ext_scorer->alpha + ext_scorer->beta;
} else {
if (c == space_id || ext_scorer->is_character_based()) {
// skip scoring the space
if (ext_scorer->is_character_based()) {
prefix_to_score = prefix_new;
} else {
prefix_to_score = prefix;
}
ngram = ext_scorer->make_ngram(prefix_to_score);
ngram_score = ext_scorer->get_log_cond_prob(ngram) * ext_scorer->alpha + ext_scorer->beta;
}
else {
if (ext_scorer->is_character_based()) {
prefix_to_score = prefix_new;
} else {
prefix_to_score = prefix;
}
ngram = ext_scorer->make_ngram(prefix_to_score);
ngram_score = ext_scorer->get_log_cond_prob(ngram) * ext_scorer->alpha + ext_scorer->beta;
}
}
log_p += ngram_score;
Expand Down
7 changes: 5 additions & 2 deletions swig/hotwords.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,8 +90,11 @@ float HotWordsScorer::get_hotwords_score(const std::vector<std::string>& words,
// word = std::accumulate(words.begin() + offset, words.end() - index, std::string{});
word = std::accumulate(words.begin() + offset + index, words.end(), std::string{});
} else {
// word in fixed window, traverse each word in words.
word = words[index];
// word in fixed window, traverse each word in words, skip <s> token.
if (index + offset >= words_size) {
break;
}
word = words[index + offset];
}
iter = this->hotwords_dict.find(word);
if (iter != this->hotwords_dict.end()) {
Expand Down