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

Add CTC HLG decoding using OpenFst (#349)

Browse Source
This commit is contained in:
Fangjun Kuang
2023-10-08 11:32:39 +08:00
committed by GitHub
parent c12286fe5e
commit 407602445d
39 changed files with 964 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
sherpa-onnx/python/csrc/CMakeLists.txt
View File

@@ -5,6 +5,7 @@ pybind11_add_module(_sherpa_onnx
display.cc
endpoint.cc
features.cc
offline-ctc-fst-decoder-config.cc
offline-lm-config.cc
offline-model-config.cc
offline-nemo-enc-dec-ctc-model-config.cc
@@ -14,6 +15,7 @@ pybind11_add_module(_sherpa_onnx
offline-tdnn-model-config.cc
offline-transducer-model-config.cc
offline-whisper-model-config.cc
offline-zipformer-ctc-model-config.cc
online-lm-config.cc
online-model-config.cc
online-paraformer-model-config.cc

23
sherpa-onnx/python/csrc/offline-ctc-fst-decoder-config.cc Normal file
View File

@@ -0,0 +1,23 @@
// sherpa-onnx/python/csrc/offline-ctc-fst-decoder-config.cc
//
// Copyright (c) 2023 Xiaomi Corporation
#include "sherpa-onnx/python/csrc/offline-ctc-fst-decoder-config.h"
#include <string>
#include "sherpa-onnx/csrc/offline-ctc-fst-decoder-config.h"
namespace sherpa_onnx {
void PybindOfflineCtcFstDecoderConfig(py::module *m) {
using PyClass = OfflineCtcFstDecoderConfig;
py::class_<PyClass>(*m, "OfflineCtcFstDecoderConfig")
.def(py::init<const std::string &, int32_t>(), py::arg("graph") = "",
py::arg("max_active") = 3000)
.def_readwrite("graph", &PyClass::graph)
.def_readwrite("max_active", &PyClass::max_active)
.def("__str__", &PyClass::ToString);
}
} // namespace sherpa_onnx

16
sherpa-onnx/python/csrc/offline-ctc-fst-decoder-config.h Normal file
View File

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

11
sherpa-onnx/python/csrc/offline-model-config.cc
View File

@@ -13,6 +13,7 @@
#include "sherpa-onnx/python/csrc/offline-tdnn-model-config.h"
#include "sherpa-onnx/python/csrc/offline-transducer-model-config.h"
#include "sherpa-onnx/python/csrc/offline-whisper-model-config.h"
#include "sherpa-onnx/python/csrc/offline-zipformer-ctc-model-config.h"
namespace sherpa_onnx {
@@ -22,6 +23,7 @@ void PybindOfflineModelConfig(py::module *m) {
PybindOfflineNemoEncDecCtcModelConfig(m);
PybindOfflineWhisperModelConfig(m);
PybindOfflineTdnnModelConfig(m);
PybindOfflineZipformerCtcModelConfig(m);
using PyClass = OfflineModelConfig;
py::class_<PyClass>(*m, "OfflineModelConfig")
@@ -29,20 +31,23 @@ void PybindOfflineModelConfig(py::module *m) {
const OfflineParaformerModelConfig &,
const OfflineNemoEncDecCtcModelConfig &,
const OfflineWhisperModelConfig &,
const OfflineTdnnModelConfig &, const std::string &,
const OfflineTdnnModelConfig &,
const OfflineZipformerCtcModelConfig &, const std::string &,
int32_t, bool, const std::string &, const std::string &>(),
py::arg("transducer") = OfflineTransducerModelConfig(),
py::arg("paraformer") = OfflineParaformerModelConfig(),
py::arg("nemo_ctc") = OfflineNemoEncDecCtcModelConfig(),
py::arg("whisper") = OfflineWhisperModelConfig(),
py::arg("tdnn") = OfflineTdnnModelConfig(), py::arg("tokens"),
py::arg("num_threads"), py::arg("debug") = false,
py::arg("tdnn") = OfflineTdnnModelConfig(),
py::arg("zipformer_ctc") = OfflineZipformerCtcModelConfig(),
py::arg("tokens"), py::arg("num_threads"), py::arg("debug") = false,
py::arg("provider") = "cpu", py::arg("model_type") = "")
.def_readwrite("transducer", &PyClass::transducer)
.def_readwrite("paraformer", &PyClass::paraformer)
.def_readwrite("nemo_ctc", &PyClass::nemo_ctc)
.def_readwrite("whisper", &PyClass::whisper)
.def_readwrite("tdnn", &PyClass::tdnn)
.def_readwrite("zipformer_ctc", &PyClass::zipformer_ctc)
.def_readwrite("tokens", &PyClass::tokens)
.def_readwrite("num_threads", &PyClass::num_threads)
.def_readwrite("debug", &PyClass::debug)

5
sherpa-onnx/python/csrc/offline-recognizer.cc
View File

@@ -16,15 +16,18 @@ static void PybindOfflineRecognizerConfig(py::module *m) {
py::class_<PyClass>(*m, "OfflineRecognizerConfig")
.def(py::init<const OfflineFeatureExtractorConfig &,
const OfflineModelConfig &, const OfflineLMConfig &,
const std::string &, int32_t, const std::string &, float>(),
const OfflineCtcFstDecoderConfig &, const std::string &,
int32_t, const std::string &, float>(),
py::arg("feat_config"), py::arg("model_config"),
py::arg("lm_config") = OfflineLMConfig(),
py::arg("ctc_fst_decoder_config") = OfflineCtcFstDecoderConfig(),
py::arg("decoding_method") = "greedy_search",
py::arg("max_active_paths") = 4, py::arg("hotwords_file") = "",
py::arg("hotwords_score") = 1.5)
.def_readwrite("feat_config", &PyClass::feat_config)
.def_readwrite("model_config", &PyClass::model_config)
.def_readwrite("lm_config", &PyClass::lm_config)
.def_readwrite("ctc_fst_decoder_config", &PyClass::ctc_fst_decoder_config)
.def_readwrite("decoding_method", &PyClass::decoding_method)
.def_readwrite("max_active_paths", &PyClass::max_active_paths)
.def_readwrite("hotwords_file", &PyClass::hotwords_file)

22
sherpa-onnx/python/csrc/offline-zipformer-ctc-model-config.cc Normal file
View File

@@ -0,0 +1,22 @@
// sherpa-onnx/python/csrc/offline-zipformer-ctc-model-config.cc
//
// Copyright (c) 2023 Xiaomi Corporation
#include "sherpa-onnx/python/csrc/offline-zipformer-ctc-model-config.h"
#include <string>
#include "sherpa-onnx/csrc/offline-zipformer-ctc-model-config.h"
namespace sherpa_onnx {
void PybindOfflineZipformerCtcModelConfig(py::module *m) {
using PyClass = OfflineZipformerCtcModelConfig;
py::class_<PyClass>(*m, "OfflineZipformerCtcModelConfig")
.def(py::init<>())
.def(py::init<const std::string &>(), py::arg("model"))
.def_readwrite("model", &PyClass::model)
.def("__str__", &PyClass::ToString);
}
} // namespace sherpa_onnx

16
sherpa-onnx/python/csrc/offline-zipformer-ctc-model-config.h Normal file
View File

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

2
sherpa-onnx/python/csrc/sherpa-onnx.cc
View File

@@ -8,6 +8,7 @@
#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-ctc-fst-decoder-config.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"
@@ -37,6 +38,7 @@ PYBIND11_MODULE(_sherpa_onnx, m) {
PybindOfflineStream(&m);
PybindOfflineLMConfig(&m);
PybindOfflineModelConfig(&m);
PybindOfflineCtcFstDecoderConfig(&m);
PybindOfflineRecognizer(&m);
PybindVadModelConfig(&m);

2
sherpa-onnx/python/sherpa_onnx/offline_recognizer.py
View File

@@ -4,12 +4,14 @@ from pathlib import Path
from typing import List, Optional
from _sherpa_onnx import (
OfflineCtcFstDecoderConfig,
OfflineFeatureExtractorConfig,
OfflineModelConfig,
OfflineNemoEncDecCtcModelConfig,
OfflineParaformerModelConfig,
OfflineTdnnModelConfig,
OfflineWhisperModelConfig,
OfflineZipformerCtcModelConfig,
)
from _sherpa_onnx import OfflineRecognizer as _Recognizer
from _sherpa_onnx import (