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

Add the scoring of last word/char of prefixes in CTC beam search decoder #427

Merged
merged 2 commits into from
Nov 7, 2017
Merged

Add the scoring of last word/char of prefixes in CTC beam search decoder #427

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
73c3a60
Add the scoring of last word/char of prefixes in CTC beam search decoder
Nov 6, 2017
0cc1a74
skip scoring the end when using character-based scorer
Nov 7, 2017
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
2 changes: 1 addition & 1 deletion .clang_format.hook
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
#!/usr/bin/env bash
set -e

readonly VERSION="3.9"
readonly VERSION="3.6"

version=$(clang-format -version)

Expand Down
28 changes: 23 additions & 5 deletions deep_speech_2/decoders/swig/ctc_beam_search_decoder.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,17 +110,17 @@ std::vector<std::pair<double, std::string>> ctc_beam_search_decoder(
// language model scoring
if (ext_scorer != nullptr &&
(c == space_id || ext_scorer->is_character_based())) {
PathTrie *prefix_toscore = nullptr;
PathTrie *prefix_to_score = nullptr;
// skip scoring the space
if (ext_scorer->is_character_based()) {
prefix_toscore = prefix_new;
prefix_to_score = prefix_new;
} else {
prefix_toscore = prefix;
prefix_to_score = prefix;
}

double score = 0.0;
float score = 0.0;
std::vector<std::string> ngram;
ngram = ext_scorer->make_ngram(prefix_toscore);
ngram = ext_scorer->make_ngram(prefix_to_score);
score = ext_scorer->get_log_cond_prob(ngram) * ext_scorer->alpha;
log_p += score;
log_p += ext_scorer->beta;
Expand All @@ -131,6 +131,7 @@ std::vector<std::pair<double, std::string>> ctc_beam_search_decoder(
} // end of loop over prefix
} // end of loop over vocabulary


prefixes.clear();
// update log probs
root.iterate_to_vec(prefixes);
Expand All @@ -147,6 +148,23 @@ std::vector<std::pair<double, std::string>> ctc_beam_search_decoder(
}
} // end of loop over time

// score the last word of each prefix that doesn't end with space
if (ext_scorer != nullptr && !ext_scorer->is_character_based()) {
for (size_t i = 0; i < beam_size && i < prefixes.size(); ++i) {
auto prefix = prefixes[i];
if (!prefix->is_empty() && prefix->character != space_id) {
float score = 0.0;
std::vector<std::string> ngram = ext_scorer->make_ngram(prefix);
score = ext_scorer->get_log_cond_prob(ngram) * ext_scorer->alpha;
score += ext_scorer->beta;
prefix->score += score;
}
}
}

size_t num_prefixes = std::min(prefixes.size(), beam_size);
std::sort(prefixes.begin(), prefixes.begin() + num_prefixes, prefix_compare);

// compute aproximate ctc score as the return score, without affecting the
// return order of decoding result. To delete when decoder gets stable.
for (size_t i = 0; i < beam_size && i < prefixes.size(); ++i) {
Expand Down