Add RNN LM rescore for offline ASR with modified_beam_search (#125)

This commit is contained in:
Fangjun Kuang
2023-04-23 17:15:18 +08:00
committed by GitHub
parent d49a597431
commit 86017f9833
32 changed files with 842 additions and 52 deletions

View File

@@ -4,6 +4,7 @@ pybind11_add_module(_sherpa_onnx
display.cc
endpoint.cc
features.cc
offline-lm-config.cc
offline-model-config.cc
offline-nemo-enc-dec-ctc-model-config.cc
offline-paraformer-model-config.cc

View File

@@ -0,0 +1,23 @@
// sherpa-onnx/python/csrc/offline-lm-config.cc
//
// Copyright (c) 2023 Xiaomi Corporation
#include "sherpa-onnx/python/csrc/offline-lm-config.h"
#include <string>
#include "sherpa-onnx//csrc/offline-lm-config.h"
namespace sherpa_onnx {
void PybindOfflineLMConfig(py::module *m) {
using PyClass = OfflineLMConfig;
py::class_<PyClass>(*m, "OfflineLMConfig")
.def(py::init<const std::string &, float>(), py::arg("model"),
py::arg("scale"))
.def_readwrite("model", &PyClass::model)
.def_readwrite("scale", &PyClass::scale)
.def("__str__", &PyClass::ToString);
}
} // namespace sherpa_onnx

View File

@@ -0,0 +1,16 @@
// sherpa-onnx/python/csrc/offline-lm-config.h
//
// Copyright (c) 2023 Xiaomi Corporation
#ifndef SHERPA_ONNX_PYTHON_CSRC_OFFLINE_LM_CONFIG_H_
#define SHERPA_ONNX_PYTHON_CSRC_OFFLINE_LM_CONFIG_H_
#include "sherpa-onnx/python/csrc/sherpa-onnx.h"
namespace sherpa_onnx {
void PybindOfflineLMConfig(py::module *m);
}
#endif // SHERPA_ONNX_PYTHON_CSRC_OFFLINE_LM_CONFIG_H_

View File

@@ -15,12 +15,17 @@ static void PybindOfflineRecognizerConfig(py::module *m) {
using PyClass = OfflineRecognizerConfig;
py::class_<PyClass>(*m, "OfflineRecognizerConfig")
.def(py::init<const OfflineFeatureExtractorConfig &,
const OfflineModelConfig &, const std::string &>(),
const OfflineModelConfig &, const OfflineLMConfig &,
const std::string &, int32_t>(),
py::arg("feat_config"), py::arg("model_config"),
py::arg("decoding_method"))
py::arg("lm_config") = OfflineLMConfig(),
py::arg("decoding_method") = "greedy_search",
py::arg("max_active_paths") = 4)
.def_readwrite("feat_config", &PyClass::feat_config)
.def_readwrite("model_config", &PyClass::model_config)
.def_readwrite("lm_config", &PyClass::lm_config)
.def_readwrite("decoding_method", &PyClass::decoding_method)
.def_readwrite("max_active_paths", &PyClass::max_active_paths)
.def("__str__", &PyClass::ToString);
}

View File

@@ -7,6 +7,7 @@
#include "sherpa-onnx/python/csrc/display.h"
#include "sherpa-onnx/python/csrc/endpoint.h"
#include "sherpa-onnx/python/csrc/features.h"
#include "sherpa-onnx/python/csrc/offline-lm-config.h"
#include "sherpa-onnx/python/csrc/offline-model-config.h"
#include "sherpa-onnx/python/csrc/offline-recognizer.h"
#include "sherpa-onnx/python/csrc/offline-stream.h"
@@ -28,6 +29,7 @@ PYBIND11_MODULE(_sherpa_onnx, m) {
PybindDisplay(&m);
PybindOfflineStream(&m);
PybindOfflineLMConfig(&m);
PybindOfflineModelConfig(&m);
PybindOfflineRecognizer(&m);
}