EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

decoder for open vocabulary keyword spotting (#505)

Browse Source 
* various fixes to ContextGraph to support open vocabulary keywords decoder

* Add keyword spotter runtime

* Add binary

* First version works

* Minor fixes

* update text2token

* default values

* Add jni for kws

* add kws android project

* Minor fixes

* Remove unused interface

* Minor fixes

* Add workflow

* handle extra info in texts

* Minor fixes

* Add more comments

* Fix ci

* fix cpp style

* Add input box in android demo so that users can specify their keywords

* Fix cpp style

* Fix comments

* Minor fixes

* Minor fixes

* minor fixes

* Minor fixes

* Minor fixes

* Add CI

* Fix code style

* cpplint

* Fix comments

* Fix error
This commit is contained in:
Wei Kang
2024-01-20 22:52:41 +08:00
committed by GitHub
parent bf1dd3daf6
commit b6c020901a
77 changed files with 3316 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
sherpa-onnx/csrc/context-graph.h
View File

@@ -6,6 +6,8 @@
#define SHERPA_ONNX_CSRC_CONTEXT_GRAPH_H_
#include <memory>
#include <string>
#include <tuple>
#include <unordered_map>
#include <utility>
#include <vector>
@@ -22,34 +24,55 @@ struct ContextState {
float token_score;
float node_score;
float output_score;
int32_t level;
float ac_threshold;
bool is_end;
std::string phrase;
std::unordered_map<int32_t, std::unique_ptr<ContextState>> next;
const ContextState *fail = nullptr;
const ContextState *output = nullptr;
ContextState() = default;
ContextState(int32_t token, float token_score, float node_score,
float output_score, bool is_end)
float output_score, int32_t level = 0, float ac_threshold = 0.0f,
bool is_end = false, const std::string &phrase = {})
: token(token),
token_score(token_score),
node_score(node_score),
output_score(output_score),
is_end(is_end) {}
level(level),
ac_threshold(ac_threshold),
is_end(is_end),
phrase(phrase) {}
};
class ContextGraph {
public:
ContextGraph() = default;
ContextGraph(const std::vector<std::vector<int32_t>> &token_ids,
float context_score)
: context_score_(context_score) {
root_ = std::make_unique<ContextState>(-1, 0, 0, 0, false);
float context_score, float ac_threshold,
const std::vector<float> &scores = {},
const std::vector<std::string> &phrases = {},
const std::vector<float> &ac_thresholds = {})
: context_score_(context_score), ac_threshold_(ac_threshold) {
root_ = std::make_unique<ContextState>(-1, 0, 0, 0);
root_->fail = root_.get();
Build(token_ids);
Build(token_ids, scores, phrases, ac_thresholds);
}
std::pair<float, const ContextState *> ForwardOneStep(
const ContextState *state, int32_t token_id) const;
ContextGraph(const std::vector<std::vector<int32_t>> &token_ids,
float context_score, const std::vector<float> &scores = {},
const std::vector<std::string> &phrases = {})
: ContextGraph(token_ids, context_score, 0.0f, scores, phrases,
std::vector<float>()) {}
std::tuple<float, const ContextState *, const ContextState *> ForwardOneStep(
const ContextState *state, int32_t token_id,
bool strict_mode = true) const;
std::pair<bool, const ContextState *> IsMatched(
const ContextState *state) const;
std::pair<float, const ContextState *> Finalize(
const ContextState *state) const;
@@ -57,8 +80,12 @@ class ContextGraph {
private:
float context_score_;
float ac_threshold_;
std::unique_ptr<ContextState> root_;
void Build(const std::vector<std::vector<int32_t>> &token_ids) const;
void Build(const std::vector<std::vector<int32_t>> &token_ids,
const std::vector<float> &scores,
const std::vector<std::string> &phrases,
const std::vector<float> &ac_thresholds) const;
void FillFailOutput() const;
};