fix(silero): keep explicit load on onnx (#1944)

Co-authored-by: rosetta-livekit-bot[bot] <282703043+rosetta-livekit-bot[bot]@users.noreply.github.com>

Author: rosetta-livekit-bot[bot]

.changeset/silero-onnx-load.md

@@ -0,0 +1,5 @@
+---
+'@livekit/agents-plugin-silero': patch
+---
+
+Use the ONNX runtime path when explicitly loading `silero.VAD.load()`.

plugins/silero/src/index.ts

@@ -5,14 +5,6 @@ import { Plugin } from '@livekit/agents';
 
 export { VAD, VADStream } from './vad.js';
 
-console.warn(
-  '@livekit/agents-plugin-silero is deprecated and will be removed in v2.0. ' +
-    'AgentSession now defaults to the bundled silero VAD (via @livekit/local-inference); ' +
-    'drop the explicit `vad=` argument entirely, pass `vad: null` to opt out, or use ' +
-    "`import { inference } from '@livekit/agents'; new inference.VAD({ model: 'silero', ... })` " +
-    'to customise options.',
-);
-
 class SileroPlugin extends Plugin {
   constructor() {
     super({

plugins/silero/src/vad.ts

@@ -6,7 +6,6 @@ import {
   VADEventType,
   VADStream as baseStream,
   VAD as baseVAD,
-  inference,
   log,
   mergeFrames,
 } from '@livekit/agents';
@@ -100,31 +99,6 @@ export class VAD extends baseVAD {
    */
   static async load(opts: Partial<VADOptions> = {}): Promise<baseVAD> {
     const mergedOpts: VADOptions = { ...defaultVADOptions, ...opts };
-
-    // When the requested settings are compatible with the bundled native
-    // implementation in `@livekit/local-inference`, delegate to
-    // `inference.VAD({ model: 'silero' })` so existing call sites transparently
-    // get the faster, COW-shared native path as part of the silero deprecation.
-    // The native lib only ships the 16 kHz model, so any other sample rate
-    // falls back to the legacy onnxruntime path below.
-    if (mergedOpts.sampleRate === 16000) {
-      if (!mergedOpts.forceCPU) {
-        log().warn(
-          'forceCPU=false is ignored when using the bundled native VAD; the ' +
-            'model runs CPU-only. Use a non-16kHz sampleRate to keep the legacy ' +
-            'onnxruntime path that honors forceCPU.',
-        );
-      }
-      return new inference.VAD({
-        model: 'silero',
-        minSpeechDuration: mergedOpts.minSpeechDuration,
-        minSilenceDuration: mergedOpts.minSilenceDuration,
-        prefixPaddingDuration: mergedOpts.prefixPaddingDuration,
-        maxBufferedSpeech: mergedOpts.maxBufferedSpeech,
-        activationThreshold: mergedOpts.activationThreshold,
-      });
-    }
-
     const session = await newInferenceSession(mergedOpts.forceCPU);
     return new VAD(session, mergedOpts);
   }