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

Encode hotwords in C++ side (#828)

Browse Source 
* Encode hotwords in C++ side
This commit is contained in:
Wei Kang
2024-05-20 19:41:36 +08:00
committed by GitHub
parent 8af2af8466
commit b012b78ceb
43 changed files with 714 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
sherpa-onnx/csrc/online-model-config.h
View File

@@ -37,6 +37,13 @@ struct OnlineModelConfig {
// All other values are invalid and lead to loading the model twice.
std::string model_type;
// Valid values:
// - cjkchar
// - bpe
// - cjkchar+bpe
std::string modeling_unit = "cjkchar";
std::string bpe_vocab;
OnlineModelConfig() = default;
OnlineModelConfig(const OnlineTransducerModelConfig &transducer,
const OnlineParaformerModelConfig &paraformer,
@@ -45,7 +52,9 @@ struct OnlineModelConfig {
const OnlineNeMoCtcModelConfig &nemo_ctc,
const std::string &tokens, int32_t num_threads,
int32_t warm_up, bool debug, const std::string &provider,
const std::string &model_type)
const std::string &model_type,
const std::string &modeling_unit,
const std::string &bpe_vocab)
: transducer(transducer),
paraformer(paraformer),
wenet_ctc(wenet_ctc),
@@ -56,7 +65,9 @@ struct OnlineModelConfig {
warm_up(warm_up),
debug(debug),
provider(provider),
model_type(model_type) {}
model_type(model_type),
modeling_unit(modeling_unit),
bpe_vocab(bpe_vocab) {}
void Register(ParseOptions *po);
bool Validate() const;