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

Add C++ and Python API for FireRedASR AED models (#1867)

Browse Source
This commit is contained in:
Fangjun Kuang
2025-02-16 22:45:24 +08:00
committed by GitHub
parent 2337169ee2
commit 316424b382
20 changed files with 1019 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
sherpa-onnx/python/csrc/CMakeLists.txt
View File

@@ -9,6 +9,7 @@ set(srcs
features.cc
keyword-spotter.cc
offline-ctc-fst-decoder-config.cc
offline-fire-red-asr-model-config.cc
offline-lm-config.cc
offline-model-config.cc
offline-moonshine-model-config.cc

24
sherpa-onnx/python/csrc/offline-fire-red-asr-model-config.cc Normal file
View File

@@ -0,0 +1,24 @@
// sherpa-onnx/python/csrc/offline-fire-red-asr-model-config.cc
//
// Copyright (c) 2025 Xiaomi Corporation
#include "sherpa-onnx/csrc/offline-fire-red-asr-model-config.h"
#include <string>
#include <vector>
#include "sherpa-onnx/python/csrc/offline-fire-red-asr-model-config.h"
namespace sherpa_onnx {
void PybindOfflineFireRedAsrModelConfig(py::module *m) {
using PyClass = OfflineFireRedAsrModelConfig;
py::class_<PyClass>(*m, "OfflineFireRedAsrModelConfig")
.def(py::init<const std::string &, const std::string &>(),
py::arg("encoder"), py::arg("decoder"))
.def_readwrite("encoder", &PyClass::encoder)
.def_readwrite("decoder", &PyClass::decoder)
.def("__str__", &PyClass::ToString);
}
} // namespace sherpa_onnx

16
sherpa-onnx/python/csrc/offline-fire-red-asr-model-config.h Normal file
View File

@@ -0,0 +1,16 @@
// sherpa-onnx/python/csrc/offline-fire-red-asr-model-config.h
//
// Copyright (c) 2025 Xiaomi Corporation
#ifndef SHERPA_ONNX_PYTHON_CSRC_OFFLINE_FIRE_RED_ASR_MODEL_CONFIG_H_
#define SHERPA_ONNX_PYTHON_CSRC_OFFLINE_FIRE_RED_ASR_MODEL_CONFIG_H_
#include "sherpa-onnx/python/csrc/sherpa-onnx.h"
namespace sherpa_onnx {
void PybindOfflineFireRedAsrModelConfig(py::module *m);
}
#endif // SHERPA_ONNX_PYTHON_CSRC_OFFLINE_FIRE_RED_ASR_MODEL_CONFIG_H_

55
sherpa-onnx/python/csrc/offline-model-config.cc
View File

@@ -8,6 +8,7 @@
#include <vector>
#include "sherpa-onnx/csrc/offline-model-config.h"
#include "sherpa-onnx/python/csrc/offline-fire-red-asr-model-config.h"
#include "sherpa-onnx/python/csrc/offline-moonshine-model-config.h"
#include "sherpa-onnx/python/csrc/offline-nemo-enc-dec-ctc-model-config.h"
#include "sherpa-onnx/python/csrc/offline-paraformer-model-config.h"
@@ -25,6 +26,7 @@ void PybindOfflineModelConfig(py::module *m) {
PybindOfflineParaformerModelConfig(m);
PybindOfflineNemoEncDecCtcModelConfig(m);
PybindOfflineWhisperModelConfig(m);
PybindOfflineFireRedAsrModelConfig(m);
PybindOfflineTdnnModelConfig(m);
PybindOfflineZipformerCtcModelConfig(m);
PybindOfflineWenetCtcModelConfig(m);
@@ -33,35 +35,38 @@ void PybindOfflineModelConfig(py::module *m) {
using PyClass = OfflineModelConfig;
py::class_<PyClass>(*m, "OfflineModelConfig")
.def(
py::init<
const OfflineTransducerModelConfig &,
const OfflineParaformerModelConfig &,
const OfflineNemoEncDecCtcModelConfig &,
const OfflineWhisperModelConfig &, const OfflineTdnnModelConfig &,
const OfflineZipformerCtcModelConfig &,
const OfflineWenetCtcModelConfig &,
const OfflineSenseVoiceModelConfig &,
const OfflineMoonshineModelConfig &, const std::string &,
const std::string &, int32_t, bool, const std::string &,
const std::string &, 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("zipformer_ctc") = OfflineZipformerCtcModelConfig(),
py::arg("wenet_ctc") = OfflineWenetCtcModelConfig(),
py::arg("sense_voice") = OfflineSenseVoiceModelConfig(),
py::arg("moonshine") = OfflineMoonshineModelConfig(),
py::arg("telespeech_ctc") = "", py::arg("tokens"),
py::arg("num_threads"), py::arg("debug") = false,
py::arg("provider") = "cpu", py::arg("model_type") = "",
py::arg("modeling_unit") = "cjkchar", py::arg("bpe_vocab") = "")
.def(py::init<const OfflineTransducerModelConfig &,
const OfflineParaformerModelConfig &,
const OfflineNemoEncDecCtcModelConfig &,
const OfflineWhisperModelConfig &,
const OfflineFireRedAsrModelConfig &,
const OfflineTdnnModelConfig &,
const OfflineZipformerCtcModelConfig &,
const OfflineWenetCtcModelConfig &,
const OfflineSenseVoiceModelConfig &,
const OfflineMoonshineModelConfig &, const std::string &,
const std::string &, int32_t, bool, const std::string &,
const std::string &, 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("fire_red_asr") = OfflineFireRedAsrModelConfig(),
py::arg("tdnn") = OfflineTdnnModelConfig(),
py::arg("zipformer_ctc") = OfflineZipformerCtcModelConfig(),
py::arg("wenet_ctc") = OfflineWenetCtcModelConfig(),
py::arg("sense_voice") = OfflineSenseVoiceModelConfig(),
py::arg("moonshine") = OfflineMoonshineModelConfig(),
py::arg("telespeech_ctc") = "", py::arg("tokens"),
py::arg("num_threads"), py::arg("debug") = false,
py::arg("provider") = "cpu", py::arg("model_type") = "",
py::arg("modeling_unit") = "cjkchar", py::arg("bpe_vocab") = "")
.def_readwrite("transducer", &PyClass::transducer)
.def_readwrite("paraformer", &PyClass::paraformer)
.def_readwrite("nemo_ctc", &PyClass::nemo_ctc)
.def_readwrite("whisper", &PyClass::whisper)
.def_readwrite("fire_red_asr", &PyClass::fire_red_asr)
.def_readwrite("tdnn", &PyClass::tdnn)
.def_readwrite("zipformer_ctc", &PyClass::zipformer_ctc)
.def_readwrite("wenet_ctc", &PyClass::wenet_ctc)

73
sherpa-onnx/python/sherpa_onnx/offline_recognizer.py
View File

@@ -6,6 +6,7 @@ from typing import List, Optional
from _sherpa_onnx import (
FeatureExtractorConfig,
OfflineCtcFstDecoderConfig,
OfflineFireRedAsrModelConfig,
OfflineLMConfig,
OfflineModelConfig,
OfflineMoonshineModelConfig,
@@ -571,6 +572,78 @@ class OfflineRecognizer(object):
self.config = recognizer_config
return self
@classmethod
def from_fire_red_asr(
cls,
encoder: str,
decoder: str,
tokens: str,
num_threads: int = 1,
decoding_method: str = "greedy_search",
debug: bool = False,
provider: str = "cpu",
rule_fsts: str = "",
rule_fars: str = "",
):
"""
Please refer to
`<https://k2-fsa.github.io/sherpa/onnx/fire_red_asr/index.html>`_
to download pre-trained models for different kinds of FireRedAsr models,
e.g., xs, large, etc.
Args:
encoder:
Path to the encoder model.
decoder:
Path to the decoder model.
tokens:
Path to ``tokens.txt``. Each line in ``tokens.txt`` contains two
columns::
symbol integer_id
num_threads:
Number of threads for neural network computation.
decoding_method:
Valid values: greedy_search.
debug:
True to show debug messages.
provider:
onnxruntime execution providers. Valid values are: cpu, cuda, coreml.
rule_fsts:
If not empty, it specifies fsts for inverse text normalization.
If there are multiple fsts, they are separated by a comma.
rule_fars:
If not empty, it specifies fst archives for inverse text normalization.
If there are multiple archives, they are separated by a comma.
"""
self = cls.__new__(cls)
model_config = OfflineModelConfig(
fire_red_asr=OfflineFireRedAsrModelConfig(
encoder=encoder,
decoder=decoder,
),
tokens=tokens,
num_threads=num_threads,
debug=debug,
provider=provider,
)
feat_config = FeatureExtractorConfig(
sampling_rate=16000,
feature_dim=80,
)
recognizer_config = OfflineRecognizerConfig(
feat_config=feat_config,
model_config=model_config,
decoding_method=decoding_method,
rule_fsts=rule_fsts,
rule_fars=rule_fars,
)
self.recognizer = _Recognizer(recognizer_config)
self.config = recognizer_config
return self
@classmethod
def from_moonshine(
cls,