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

Refactor online recognizer (#250)

Browse Source 
* Refactor online recognizer.

Make it easier to support other streaming models.

Note that it is a breaking change for the Python API.
`sherpa_onnx.OnlineRecognizer()` used before should be
replaced by `sherpa_onnx.OnlineRecognizer.from_transducer()`.
This commit is contained in:
Fangjun Kuang
2023-08-09 20:27:31 +08:00
committed by GitHub
parent 6061318e3f
commit 79c2ce5dd4
40 changed files with 670 additions and 480 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
sherpa-onnx/csrc/online-recognizer-impl.cc Normal file
View File

@@ -0,0 +1,33 @@
// sherpa-onnx/csrc/online-recognizer-impl.cc
//
// Copyright (c) 2023 Xiaomi Corporation
#include "sherpa-onnx/csrc/online-recognizer-impl.h"
#include "sherpa-onnx/csrc/online-recognizer-transducer-impl.h"
namespace sherpa_onnx {
std::unique_ptr<OnlineRecognizerImpl> OnlineRecognizerImpl::Create(
const OnlineRecognizerConfig &config) {
if (!config.model_config.transducer.encoder.empty()) {
return std::make_unique<OnlineRecognizerTransducerImpl>(config);
}
SHERPA_ONNX_LOGE("Please specify a model");
exit(-1);
}
#if __ANDROID_API__ >= 9
std::unique_ptr<OnlineRecognizerImpl> OnlineRecognizerImpl::Create(
AAssetManager *mgr, const OnlineRecognizerConfig &config) {
if (!config.model_config.transducer.encoder.empty()) {
return std::make_unique<OnlineRecognizerTransducerImpl>(mgr, config);
}
SHERPA_ONNX_LOGE("Please specify a model");
exit(-1);
}
#endif
} // namespace sherpa_onnx