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

Re-implement LM rescore for online transducer (#1231)

Browse Source 
Co-authored-by: Martins Kronis <martins.kuznecovs@tilde.lv>
This commit is contained in:
SilverSulfide
2024-09-06 05:01:25 +03:00
committed by GitHub
parent 1f29e4a1a9
commit 888f74bf3c
11 changed files with 175 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
sherpa-onnx/csrc/online-lm-config.cc
View File

@@ -18,6 +18,8 @@ void OnlineLMConfig::Register(ParseOptions *po) {
"Number of threads to run the neural network of LM model");
po->Register("lm-provider", &lm_provider,
"Specify a provider to LM model use: cpu, cuda, coreml");
po->Register("lm-shallow-fusion", &shallow_fusion,
"Boolean whether to use shallow fusion or rescore.");
}
bool OnlineLMConfig::Validate() const {
@@ -34,7 +36,8 @@ std::string OnlineLMConfig::ToString() const {
os << "OnlineLMConfig(";
os << "model=\"" << model << "\", ";
os << "scale=" << scale << ")";
os << "scale=" << scale << ", ";
os << "shallow_fusion=" << (shallow_fusion ? "True" : "False") << ")";
return os.str();
}