sherpa-onnx-node 1.12.28 → 1.12.30

package/addon.js

@@ -51,7 +51,7 @@ if (!addon) {
        !process.env.DYLD_LIBRARY_PATH.includes(
            `node_modules/sherpa-onnx-${platform_arch}`))) {
     msg +=
-        'Please remeber to set the following environment variable and try again:\n';
+        'Please remember to set the following environment variable and try again:\n';
 
     msg += `export DYLD_LIBRARY_PATH=${addon_path}`;
 
@@ -63,7 +63,7 @@ if (!addon) {
        !process.env.LD_LIBRARY_PATH.includes(
            `node_modules/sherpa-onnx-${platform_arch}`))) {
     msg +=
-        'Please remeber to set the following environment variable and try again:\n';
+        'Please remember to set the following environment variable and try again:\n';
 
     msg += `export LD_LIBRARY_PATH=${addon_path}`;
 

package/online-speech-denoiser.js

@@ -0,0 +1,45 @@
+/** @typedef {import('./types').OnlineSpeechDenoiserConfig} OnlineSpeechDenoiserConfig */
+/** @typedef {import('./types').GeneratedAudio} GeneratedAudio */
+/** @typedef {import('./types').AudioProcessRequest} AudioProcessRequest */
+
+const addon = require('./addon.js');
+
+class OnlineSpeechDenoiser {
+  /**
+   * @param {OnlineSpeechDenoiserConfig} config
+   */
+  constructor(config) {
+    this.handle = addon.createOnlineSpeechDenoiser(config);
+    this.config = config;
+
+    this.sampleRate =
+        addon.onlineSpeechDenoiserGetSampleRateWrapper(this.handle);
+    this.frameShiftInSamples =
+        addon.onlineSpeechDenoiserGetFrameShiftInSamplesWrapper(this.handle);
+  }
+
+  /**
+   * @param {AudioProcessRequest} obj
+   * @returns {GeneratedAudio}
+   */
+  run(obj) {
+    return addon.onlineSpeechDenoiserRunWrapper(this.handle, obj);
+  }
+
+  /**
+   * @param {boolean} [enableExternalBuffer=true]
+   * @returns {GeneratedAudio}
+   */
+  flush(enableExternalBuffer = true) {
+    return addon.onlineSpeechDenoiserFlushWrapper(
+        this.handle, enableExternalBuffer);
+  }
+
+  reset() {
+    addon.onlineSpeechDenoiserResetWrapper(this.handle);
+  }
+}
+
+module.exports = {
+  OnlineSpeechDenoiser,
+};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sherpa-onnx-node",
-  "version": "1.12.28",
+  "version": "1.12.30",
   "description": "Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection",
   "main": "sherpa-onnx.js",
   "scripts": {
@@ -57,11 +57,11 @@
   },
   "homepage": "https://github.com/csukuangfj/sherpa-onnx#readme",
   "optionalDependencies": {
-    "sherpa-onnx-darwin-arm64": "^1.12.28",
-    "sherpa-onnx-darwin-x64": "^1.12.28",
-    "sherpa-onnx-linux-x64": "^1.12.28",
-    "sherpa-onnx-linux-arm64": "^1.12.28",
-    "sherpa-onnx-win-x64": "^1.12.28",
-    "sherpa-onnx-win-ia32": "^1.12.28"
+    "sherpa-onnx-darwin-arm64": "^1.12.30",
+    "sherpa-onnx-darwin-x64": "^1.12.30",
+    "sherpa-onnx-linux-x64": "^1.12.30",
+    "sherpa-onnx-linux-arm64": "^1.12.30",
+    "sherpa-onnx-win-x64": "^1.12.30",
+    "sherpa-onnx-win-ia32": "^1.12.30"
   }
 }

package/sherpa-onnx.js

@@ -18,6 +18,7 @@ const punct = require('./punctuation.js');
 const kws = require('./keyword-spotter.js');
 const sd = require('./non-streaming-speaker-diarization.js');
 const speech_denoiser = require('./non-streaming-speech-denoiser.js');
+const online_speech_denoiser = require('./online-speech-denoiser.js');
 
 module.exports = {
   OnlineRecognizer : streaming_asr.OnlineRecognizer,
@@ -38,6 +39,7 @@ module.exports = {
   KeywordSpotter : kws.KeywordSpotter,
   OfflineSpeakerDiarization : sd.OfflineSpeakerDiarization,
   OfflineSpeechDenoiser : speech_denoiser.OfflineSpeechDenoiser,
+  OnlineSpeechDenoiser : online_speech_denoiser.OnlineSpeechDenoiser,
   version : addon.version,
   gitSha1 : addon.gitSha1,
   gitDate : addon.gitDate,

package/types.js

@@ -52,7 +52,7 @@
 
 /**
  * @typedef {Object} OfflinePunctuationHandle
- * @see src/punctuation.cc
+ * @see src/offline-punctuation.cc
  */
 
 /**
@@ -501,10 +501,24 @@
  * @property {number} [lengthScale]
  */
 
-/**
- * @typedef {Object} OfflineTtsPocketModelConfig
- * @property {string} [lmFlow]
- * @property {string} [lmMain]
+/**
+ * @typedef {Object} OfflineTtsZipvoiceModelConfig
+ * @property {string} [tokens]
+ * @property {string} [encoder]
+ * @property {string} [decoder]
+ * @property {string} [vocoder]
+ * @property {string} [dataDir]
+ * @property {string} [lexicon]
+ * @property {number} [featScale]
+ * @property {number} [tShift]
+ * @property {number} [targetRms]
+ * @property {number} [guidanceScale]
+ */
+
+/**
+ * @typedef {Object} OfflineTtsPocketModelConfig
+ * @property {string} [lmFlow]
+ * @property {string} [lmMain]
  * @property {string} [encoder]
  * @property {string} [decoder]
  * @property {string} [textConditioner]
@@ -517,11 +531,12 @@
  * Offline TTS model config
  * @typedef {Object} OfflineTtsModelConfig
  * @property {OfflineTtsVitsModelConfig} [vits]
- * @property {OfflineTtsMatchaModelConfig} [matcha]
- * @property {OfflineTtsKokoroModelConfig} [kokoro]
- * @property {OfflineTtsKittenModelConfig} [kitten]
- * @property {OfflineTtsPocketModelConfig} [pocket]
- */
+ * @property {OfflineTtsMatchaModelConfig} [matcha]
+ * @property {OfflineTtsKokoroModelConfig} [kokoro]
+ * @property {OfflineTtsKittenModelConfig} [kitten]
+ * @property {OfflineTtsZipvoiceModelConfig} [zipvoice]
+ * @property {OfflineTtsPocketModelConfig} [pocket]
+ */
 
 /**
  * Offline TTS configuration (partial, commonly used props).
@@ -533,25 +548,39 @@
  * @property {string} [provider]
  */
 
-/**
- * Offline Speech Denoiser model config
- * @typedef {Object} OfflineSpeechDenoiserGtcrnModelConfig
- * @property {string} [model]
- */
-
-/**
- * Offline Speech Denoiser model config
- * @typedef {Object} OfflineSpeechDenoiserModelConfig
- * @property {OfflineSpeechDenoiserGtcrnModelConfig} [gtcrn]
- */
-
-/**
- * Offline Speech Denoiser configuration (partial).
- * @typedef {Object} OfflineSpeechDenoiserConfig
- * @property {OfflineSpeechDenoiserModelConfig} [model]
- * @property {number} [numThreads]
- * @property {string} [provider]
- */
+/**
+ * Offline Speech Denoiser model config
+ * @typedef {Object} OfflineSpeechDenoiserGtcrnModelConfig
+ * @property {string} [model]
+ */
+
+/**
+ * Offline Speech Denoiser model config
+ * @typedef {Object} OfflineSpeechDenoiserDpdfNetModelConfig
+ * @property {string} [model]
+ */
+
+/**
+ * Offline Speech Denoiser model config
+ * @typedef {Object} OfflineSpeechDenoiserModelConfig
+ * @property {OfflineSpeechDenoiserGtcrnModelConfig} [gtcrn]
+ * @property {OfflineSpeechDenoiserDpdfNetModelConfig} [dpdfnet]
+ * @property {number} [numThreads]
+ * @property {boolean|number} [debug]
+ * @property {string} [provider]
+ */
+
+/**
+ * Offline Speech Denoiser configuration (partial).
+ * @typedef {Object} OfflineSpeechDenoiserConfig
+ * @property {OfflineSpeechDenoiserModelConfig} [model]
+ */
+
+/**
+ * Online Speech Denoiser configuration (partial).
+ * @typedef {Object} OnlineSpeechDenoiserConfig
+ * @property {OfflineSpeechDenoiserModelConfig} [model]
+ */
 
 /**
  * Offline speaker segmentation (pyannote) model config