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

Add C++ runtime for non-streaming faster conformer transducer from NeMo. (#854)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-05-10 12:15:39 +08:00
committed by GitHub
parent 5d8c35e44e
commit 17cd3a5f01
31 changed files with 1093 additions and 153 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
sherpa-onnx/python/csrc/offline-recognizer.cc
View File

@@ -14,10 +14,10 @@ namespace sherpa_onnx {
static void PybindOfflineRecognizerConfig(py::module *m) {
using PyClass = OfflineRecognizerConfig;
py::class_<PyClass>(*m, "OfflineRecognizerConfig")
.def(py::init<const OfflineFeatureExtractorConfig &,
const OfflineModelConfig &, const OfflineLMConfig &,
const OfflineCtcFstDecoderConfig &, const std::string &,
int32_t, const std::string &, float, float>(),
.def(py::init<const FeatureExtractorConfig &, const OfflineModelConfig &,
const OfflineLMConfig &, const OfflineCtcFstDecoderConfig &,
const std::string &, int32_t, const std::string &, float,
float>(),
py::arg("feat_config"), py::arg("model_config"),
py::arg("lm_config") = OfflineLMConfig(),
py::arg("ctc_fst_decoder_config") = OfflineCtcFstDecoderConfig(),