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

Support passing utf-8 strings from JavaScript to C++. (#1355)

Browse Source 
We first convert utf-16 strings to Uint8Array and then we
pass the array to C++.
This commit is contained in:
Fangjun Kuang
2024-09-18 11:03:42 +08:00
committed by GitHub
parent bf06b268d0
commit cddac52780
3 changed files with 34 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
nodejs-addon-examples/package.json
View File

@@ -1,5 +1,5 @@
{ {
"dependencies": { "dependencies": {
"sherpa-onnx-node": "^1.10.26" "sherpa-onnx-node": "^1.10.27"
} }
} }

15
nodejs-addon-examples/test_asr_non_streaming_sense_voice.js
View File

@@ -3,6 +3,19 @@ const sherpa_onnx = require('sherpa-onnx-node');
// Please download test files from // Please download test files from
// https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models // https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models
// If your path contains non-ascii characters, e.g., Chinese, you can use
// the following code
//
// let encoder = new TextEncoder();
// let tokens = encoder.encode(
// './sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/测试.txt');
// let model = encoder.encode(
// './sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/测试.int8.onnx');
const config = { const config = {
'featConfig': { 'featConfig': {
'sampleRate': 16000, 'sampleRate': 16000,
@@ -12,9 +25,11 @@ const config = {
'senseVoice': { 'senseVoice': {
'model': 'model':
'./sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/model.int8.onnx', './sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/model.int8.onnx',
// 'model': model,
'useInverseTextNormalization': 1, 'useInverseTextNormalization': 1,
}, },
'tokens': './sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/tokens.txt', 'tokens': './sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/tokens.txt',
// 'tokens': tokens,
'numThreads': 2, 'numThreads': 2,
'provider': 'cpu', 'provider': 'cpu',
'debug': 1, 'debug': 1,

29
scripts/node-addon-api/src/macros.h
View File

@@ -7,17 +7,24 @@
#include <algorithm> #include <algorithm>
#include <string> #include <string>
#define SHERPA_ONNX_ASSIGN_ATTR_STR(c_name, js_name) \ #define SHERPA_ONNX_ASSIGN_ATTR_STR(c_name, js_name) \
do { \ do { \
if (o.Has(#js_name) && o.Get(#js_name).IsString()) { \ if (o.Has(#js_name) && o.Get(#js_name).IsString()) { \
Napi::String _str = o.Get(#js_name).As<Napi::String>(); \ Napi::String _str = o.Get(#js_name).As<Napi::String>(); \
std::string s = _str.Utf8Value(); \ std::string s = _str.Utf8Value(); \
char *p = new char[s.size() + 1]; \ char *p = new char[s.size() + 1]; \
std::copy(s.begin(), s.end(), p); \ std::copy(s.begin(), s.end(), p); \
p[s.size()] = 0; \ p[s.size()] = 0; \
\ \
c.c_name = p; \ c.c_name = p; \
} \ } else if (o.Has(#js_name) && o.Get(#js_name).IsTypedArray()) { \
Napi::Uint8Array _array = o.Get(#js_name).As<Napi::Uint8Array>(); \
char *p = new char[_array.ElementLength() + 1]; \
std::copy(_array.Data(), _array.Data() + _array.ElementLength(), p); \
p[_array.ElementLength()] = '\0'; \
\
c.c_name = p; \
} \
} while (0) } while (0)
#define SHERPA_ONNX_ASSIGN_ATTR_INT32(c_name, js_name) \ #define SHERPA_ONNX_ASSIGN_ATTR_INT32(c_name, js_name) \