omnivad 0.2.9 → 0.2.11

package/dist/index.d.cts

@@ -155,9 +155,10 @@ interface ChunkResult {
 /**
  * Non-streaming Voice Activity Detection (WASM/ncnn backend).
  *
- * Audio format:
- *   - Int16Array: raw 16-bit PCM, converted to normalized float internally
- *   - Float32Array in [-1.0, 1.0]: normalized audio (Web Audio API format)
+ * Audio format: two types only. Wrappers dispatch by dtype to the matching
+ * C entry — never scale or cast in JS.
+ *   - Float32Array in [-1.0, 1.0] (Web Audio, soundfile, torch)
+ *   - Int16Array (raw 16-bit PCM from WAV / microphone)
  */
 
 declare class OmniVAD {
@@ -182,6 +183,9 @@ declare class OmniVAD {
 /**
  * Streaming Voice Activity Detection (WASM/ncnn backend).
  * Processes audio frame-by-frame (10ms chunks of 160 samples @ 16kHz).
+ *
+ * Audio format: Float32Array in [-1, 1] or Int16Array PCM. Wrappers
+ * dispatch by dtype; all scaling lives in the C entries.
  */
 
 declare class OmniStreamVAD {
@@ -200,14 +204,19 @@ declare class OmniStreamVAD {
      */
     clone(): OmniStreamVAD;
     /**
-     * Process one frame of audio (160 int16 samples = 10ms @ 16kHz).
+     * Process one frame of audio (160 samples = 10ms @ 16kHz).
+     *
+     * Accepts Float32Array in [-1, 1] (Web Audio, soundfile, torch) or
+     * Int16Array PCM (WAV, microphone). Dispatches by dtype to the matching
+     * C entry — no scaling in JS.
+     *
      * Returns null until enough audio is accumulated.
      *
      * Segment-boundary events (isSpeechStart / isSpeechEnd and the matching
      * speech_*_frame indices) come straight from the C-layer state machine
      * (bit-identical to upstream FireRedVAD) — the wrapper is just a marshaller.
      */
-    processFrame(pcm160: Int16Array): StreamVADFrameResult | null;
+    processFrame(audio: Float32Array | Int16Array): StreamVADFrameResult | null;
     /**
      * Process entire audio at once and return per-frame probabilities.
      * @param audio - Float32Array in [-1, 1] or Int16Array of 16kHz mono PCM
@@ -222,7 +231,8 @@ declare class OmniStreamVAD {
 /**
  * Audio Event Detection: speech, singing, music (WASM/ncnn backend).
  *
- * Audio format: same as OmniVAD — Int16Array or normalized Float32Array [-1, 1].
+ * Audio format: same as OmniVAD — Float32Array in [-1, 1] or Int16Array PCM.
+ * Wrappers dispatch by dtype; all scaling lives in the C entries.
  */
 
 declare class OmniAED {
@@ -250,9 +260,9 @@ declare class OmniAED {
  */
 type EmscriptenModule = any;
 /** Package version — used to construct default CDN URLs. */
-declare const VERSION = "0.2.9";
+declare const VERSION = "0.2.10";
 /** Default CDN base for model files (jsDelivr serves npm package contents). */
-declare const DEFAULT_CDN_BASE = "https://cdn.jsdelivr.net/npm/omnivad@0.2.9/models";
+declare const DEFAULT_CDN_BASE = "https://cdn.jsdelivr.net/npm/omnivad@0.2.10/models";
 /** Model filenames keyed by type. */
 declare const MODEL_FILES: {
     readonly vad: "vad.omnivad";

package/dist/index.d.ts

@@ -155,9 +155,10 @@ interface ChunkResult {
 /**
  * Non-streaming Voice Activity Detection (WASM/ncnn backend).
  *
- * Audio format:
- *   - Int16Array: raw 16-bit PCM, converted to normalized float internally
- *   - Float32Array in [-1.0, 1.0]: normalized audio (Web Audio API format)
+ * Audio format: two types only. Wrappers dispatch by dtype to the matching
+ * C entry — never scale or cast in JS.
+ *   - Float32Array in [-1.0, 1.0] (Web Audio, soundfile, torch)
+ *   - Int16Array (raw 16-bit PCM from WAV / microphone)
  */
 
 declare class OmniVAD {
@@ -182,6 +183,9 @@ declare class OmniVAD {
 /**
  * Streaming Voice Activity Detection (WASM/ncnn backend).
  * Processes audio frame-by-frame (10ms chunks of 160 samples @ 16kHz).
+ *
+ * Audio format: Float32Array in [-1, 1] or Int16Array PCM. Wrappers
+ * dispatch by dtype; all scaling lives in the C entries.
  */
 
 declare class OmniStreamVAD {
@@ -200,14 +204,19 @@ declare class OmniStreamVAD {
      */
     clone(): OmniStreamVAD;
     /**
-     * Process one frame of audio (160 int16 samples = 10ms @ 16kHz).
+     * Process one frame of audio (160 samples = 10ms @ 16kHz).
+     *
+     * Accepts Float32Array in [-1, 1] (Web Audio, soundfile, torch) or
+     * Int16Array PCM (WAV, microphone). Dispatches by dtype to the matching
+     * C entry — no scaling in JS.
+     *
      * Returns null until enough audio is accumulated.
      *
      * Segment-boundary events (isSpeechStart / isSpeechEnd and the matching
      * speech_*_frame indices) come straight from the C-layer state machine
      * (bit-identical to upstream FireRedVAD) — the wrapper is just a marshaller.
      */
-    processFrame(pcm160: Int16Array): StreamVADFrameResult | null;
+    processFrame(audio: Float32Array | Int16Array): StreamVADFrameResult | null;
     /**
      * Process entire audio at once and return per-frame probabilities.
      * @param audio - Float32Array in [-1, 1] or Int16Array of 16kHz mono PCM
@@ -222,7 +231,8 @@ declare class OmniStreamVAD {
 /**
  * Audio Event Detection: speech, singing, music (WASM/ncnn backend).
  *
- * Audio format: same as OmniVAD — Int16Array or normalized Float32Array [-1, 1].
+ * Audio format: same as OmniVAD — Float32Array in [-1, 1] or Int16Array PCM.
+ * Wrappers dispatch by dtype; all scaling lives in the C entries.
  */
 
 declare class OmniAED {
@@ -250,9 +260,9 @@ declare class OmniAED {
  */
 type EmscriptenModule = any;
 /** Package version — used to construct default CDN URLs. */
-declare const VERSION = "0.2.9";
+declare const VERSION = "0.2.10";
 /** Default CDN base for model files (jsDelivr serves npm package contents). */
-declare const DEFAULT_CDN_BASE = "https://cdn.jsdelivr.net/npm/omnivad@0.2.9/models";
+declare const DEFAULT_CDN_BASE = "https://cdn.jsdelivr.net/npm/omnivad@0.2.10/models";
 /** Model filenames keyed by type. */
 declare const MODEL_FILES: {
     readonly vad: "vad.omnivad";

package/dist/index.js

@@ -35,7 +35,7 @@ var SIZEOF_AED_SEGMENT = 16;
 var SIZEOF_CHUNK_CONFIG = 28;
 var SIZEOF_CHUNK = 16;
 var OMNI_ERR_NO_FRAMES = -7;
-var VERSION = "0.2.9";
+var VERSION = "0.2.10";
 var DEFAULT_CDN_BASE = `https://cdn.jsdelivr.net/npm/omnivad@${VERSION}/models`;
 var MODEL_FILES = {
   vad: "vad.omnivad",
@@ -160,6 +160,23 @@ function copyAudioToHeap(M, audio) {
   heap.set(audio);
   return ptr;
 }
+function copyInt16ToHeap(M, audio) {
+  const ptr = M._malloc(audio.length * 2);
+  const heap = new Int16Array(M.HEAPU8.buffer, ptr, audio.length);
+  heap.set(audio);
+  return ptr;
+}
+function dispatchAudio(M, audio) {
+  if (audio instanceof Float32Array) {
+    return { ptr: copyAudioToHeap(M, audio), length: audio.length, format: "f32" };
+  }
+  if (audio instanceof Int16Array) {
+    return { ptr: copyInt16ToHeap(M, audio), length: audio.length, format: "int16" };
+  }
+  throw new TypeError(
+    `unsupported audio dtype; expected Float32Array in [-1, 1] or Int16Array`
+  );
+}
 function writePostConfig(M, ptr, cfg) {
   M.setValue(ptr + 0, cfg.threshold, "float");
   M.setValue(ptr + 4, cfg.smoothWindowSize, "i32");
@@ -399,14 +416,15 @@ function streamVadCreate(M, modelBuffer, config = {}) {
   }
 }
 var SIZEOF_STREAM_VAD_RESULT = 24;
-function streamVadProcess(M, handle, pcm16Ptr, numSamples) {
+function streamVadProcess(M, handle, audioPtr, numSamples, format = "f32") {
   const resultPtr = M._malloc(SIZEOF_STREAM_VAD_RESULT);
+  const fn = format === "int16" ? "omni_stream_vad_process_int16" : "omni_stream_vad_process";
   try {
     const ret = M.ccall(
-      "omni_stream_vad_process",
+      fn,
       "number",
       ["number", "number", "number", "number"],
-      [handle, pcm16Ptr, numSamples, resultPtr]
+      [handle, audioPtr, numSamples, resultPtr]
     );
     if (ret === OMNI_ERR_NO_FRAMES) return null;
     if (ret !== 0) throw new Error(`StreamVAD process failed: ${ret}`);
@@ -424,6 +442,28 @@ function streamVadProcess(M, handle, pcm16Ptr, numSamples) {
     M._free(resultPtr);
   }
 }
+function streamVadDetectFull(M, handle, audioPtr, numSamples, format = "f32") {
+  const probsPtrPtr = M._malloc(4);
+  const framesPtr = M._malloc(4);
+  const fn = format === "int16" ? "omni_stream_vad_detect_full_int16" : "omni_stream_vad_detect_full";
+  try {
+    const ret = M.ccall(
+      fn,
+      "number",
+      ["number", "number", "number", "number", "number"],
+      [handle, audioPtr, numSamples, probsPtrPtr, framesPtr]
+    );
+    if (ret !== 0) throw new Error(`StreamVAD detectFull failed: ${ret}`);
+    const numFrames = M.getValue(framesPtr, "i32");
+    const probsPtr = M.getValue(probsPtrPtr, "i32");
+    const probabilities = probsPtr ? new Float32Array(new Float32Array(M.HEAPU8.buffer, probsPtr, numFrames)) : new Float32Array(0);
+    if (probsPtr) M._free(probsPtr);
+    return { probabilities, numFrames };
+  } finally {
+    M._free(probsPtrPtr);
+    M._free(framesPtr);
+  }
+}
 function streamVadClone(M, handle) {
   const errPtr = M._malloc(4);
   try {
@@ -483,7 +523,7 @@ var OmniVAD = class _OmniVAD {
    */
   detect(audio) {
     const M = getModule();
-    const { ptr, length, format } = prepareAudio(M, audio);
+    const { ptr, length, format } = dispatchAudio(M, audio);
     try {
       const timestamps = vadDetect(M, this.handle, ptr, length, this.config, format);
       return {
@@ -502,16 +542,6 @@ var OmniVAD = class _OmniVAD {
     }
   }
 };
-function prepareAudio(M, audio) {
-  const f32 = audio instanceof Int16Array ? int16ToNormalizedFloat32(audio) : audio;
-  const ptr = copyAudioToHeap(M, f32);
-  return { ptr, length: f32.length, format: "f32" };
-}
-function int16ToNormalizedFloat32(i16) {
-  const f32 = new Float32Array(i16.length);
-  for (let i = 0; i < i16.length; i++) f32[i] = i16[i] / 32768;
-  return f32;
-}
 
 // src/stream-vad.ts
 var SAMPLE_RATE2 = 16e3;
@@ -550,20 +580,23 @@ var OmniStreamVAD = class _OmniStreamVAD {
     return new _OmniStreamVAD(newHandle);
   }
   /**
-   * Process one frame of audio (160 int16 samples = 10ms @ 16kHz).
+   * Process one frame of audio (160 samples = 10ms @ 16kHz).
+   *
+   * Accepts Float32Array in [-1, 1] (Web Audio, soundfile, torch) or
+   * Int16Array PCM (WAV, microphone). Dispatches by dtype to the matching
+   * C entry — no scaling in JS.
+   *
    * Returns null until enough audio is accumulated.
    *
    * Segment-boundary events (isSpeechStart / isSpeechEnd and the matching
    * speech_*_frame indices) come straight from the C-layer state machine
    * (bit-identical to upstream FireRedVAD) — the wrapper is just a marshaller.
    */
-  processFrame(pcm160) {
+  processFrame(audio) {
     const M = getModule();
-    const ptr = M._malloc(pcm160.length * 2);
-    const heap16 = new Int16Array(M.HEAPU8.buffer, ptr, pcm160.length);
-    heap16.set(pcm160);
+    const { ptr, length, format } = dispatchAudio(M, audio);
     try {
-      const result = streamVadProcess(M, this.handle, ptr, pcm160.length);
+      const result = streamVadProcess(M, this.handle, ptr, length, format);
       if (!result) return null;
       return {
         confidence: result.confidence,
@@ -585,31 +618,22 @@ var OmniStreamVAD = class _OmniStreamVAD {
    */
   detectFull(audio) {
     const M = getModule();
-    const f32 = prepareDetectFullAudio(audio);
-    const audioPtr = copyAudioToHeap(M, f32);
-    const probsPtrPtr = M._malloc(4);
-    const framesPtr = M._malloc(4);
+    const { ptr, length, format } = dispatchAudio(M, audio);
     try {
-      const ret = M.ccall(
-        "omni_stream_vad_detect_full",
-        "number",
-        ["number", "number", "number", "number", "number"],
-        [this.handle, audioPtr, f32.length, probsPtrPtr, framesPtr]
+      const { probabilities, numFrames } = streamVadDetectFull(
+        M,
+        this.handle,
+        ptr,
+        length,
+        format
       );
-      if (ret !== 0) throw new Error(`StreamVAD detectFull failed: ${ret}`);
-      const numFrames = M.getValue(framesPtr, "i32");
-      const probsPtr = M.getValue(probsPtrPtr, "i32");
-      const probabilities = probsPtr ? new Float32Array(new Float32Array(M.HEAPU8.buffer, probsPtr, numFrames)) : new Float32Array(0);
-      if (probsPtr) M._free(probsPtr);
       return {
         probabilities,
         numFrames,
-        duration: Math.round(f32.length / SAMPLE_RATE2 * 1e3) / 1e3
+        duration: Math.round(length / SAMPLE_RATE2 * 1e3) / 1e3
       };
     } finally {
-      M._free(audioPtr);
-      M._free(probsPtrPtr);
-      M._free(framesPtr);
+      M._free(ptr);
     }
   }
   /** Reset all internal state (model cache, audio buffer, postprocessor). */
@@ -624,31 +648,6 @@ var OmniStreamVAD = class _OmniStreamVAD {
     }
   }
 };
-function int16ToFloat32(i16) {
-  const f32 = new Float32Array(i16.length);
-  for (let i = 0; i < i16.length; i++) f32[i] = i16[i];
-  return f32;
-}
-function prepareDetectFullAudio(audio) {
-  if (audio instanceof Int16Array) {
-    return int16ToFloat32(audio);
-  }
-  if (isNormalizedFloat(audio)) {
-    const scaled = new Float32Array(audio.length);
-    for (let i = 0; i < audio.length; i++) scaled[i] = audio[i] * 32768;
-    return scaled;
-  }
-  return audio;
-}
-function isNormalizedFloat(audio) {
-  const step = Math.max(1, Math.floor(audio.length / 1e3));
-  let maxAbs = 0;
-  for (let i = 0; i < audio.length; i += step) {
-    const v = Math.abs(audio[i]);
-    if (v > maxAbs) maxAbs = v;
-  }
-  return maxAbs <= 1;
-}
 
 // src/aed.ts
 var SAMPLE_RATE3 = 16e3;
@@ -688,7 +687,7 @@ var OmniAED = class _OmniAED {
    */
   detect(audio) {
     const M = getModule();
-    const { ptr, length, format } = prepareAudio2(M, audio);
+    const { ptr, length, format } = dispatchAudio(M, audio);
     const duration = Math.round(length / SAMPLE_RATE3 * 1e3) / 1e3;
     try {
       const events = aedDetect(M, this.handle, ptr, length, this.config, format);
@@ -709,18 +708,6 @@ var OmniAED = class _OmniAED {
     }
   }
 };
-function prepareAudio2(M, audio) {
-  const f32 = audio instanceof Int16Array ? int16ToNormalizedFloat322(audio) : audio;
-  const ptr = M._malloc(f32.length * 4);
-  const heap = new Float32Array(M.HEAPU8.buffer, ptr, f32.length);
-  heap.set(f32);
-  return { ptr, length: f32.length, format: "f32" };
-}
-function int16ToNormalizedFloat322(i16) {
-  const f32 = new Float32Array(i16.length);
-  for (let i = 0; i < i16.length; i++) f32[i] = i16[i] / 32768;
-  return f32;
-}
 function computeCoverageRatios(events, duration) {
   const ratios = {
     speech: 0,