fetch latest phonemis version

Author: IgorSwat

apps/speech/screens/SpeechToTextScreen.tsx

@@ -53,7 +53,7 @@ export const SpeechToTextScreen = ({ onBack }: { onBack: () => void }) => {
 
   const model = useSpeechToText({
     model: selectedModel,
-    vad: vad.fsmn_vad()
+    vad: vad.fsmn_vad(),
   });
 
   const [transcription, setTranscription] =
@@ -117,7 +117,6 @@ export const SpeechToTextScreen = ({ onBack }: { onBack: () => void }) => {
 
     Keyboard.dismiss();
 
-    const uri = await getAudioFile(audioURL);
     // Reset previous states
     setTranscription(null);
     setLiveResult(null);

docs/docs/04-typescript-api/01-natural-language-processing/SpeechToTextModule.md

@@ -14,16 +14,12 @@ The `SpeechToTextModule` class provides a direct interface to the library's spee
 You can transcribe audio in two ways: **one-shot** (for files/short clips) and **streaming** (for live microphone input).
 
 ```typescript
-import {
-  SpeechToTextModule,
-  WHISPER_TINY_EN,
-  FSMN_VAD,
-} from 'react-native-executorch';
+import { SpeechToTextModule, models } from 'react-native-executorch';
 
 // Initialize the model with VAD submodule
 const model = await SpeechToTextModule.fromModelName(
-  WHISPER_TINY_EN,
-  FSMN_VAD, // Optional VAD submodule
+  models.speech_to_text.whisper_tiny_en(),
+  models.vad.fsmn_vad(), // Optional VAD submodule
   (progress) => {
     console.log(`Loading: ${progress * 100}%`);
   }
@@ -90,14 +86,13 @@ The `stream()` function accepts several optional parameters:
 In this example, we use [`react-native-audio-api`](https://docs.swmansion.com/react-native-audio-api/) to feed live audio into the model.
 
 ```tsx
-import {
-  SpeechToTextModule,
-  WHISPER_TINY_EN,
-  FSMN_VAD,
-} from 'react-native-executorch';
+import { SpeechToTextModule, models } from 'react-native-executorch';
 import { AudioManager, AudioRecorder } from 'react-native-audio-api';
 
-const model = await SpeechToTextModule.fromModelName(WHISPER_TINY_EN, FSMN_VAD);
+const model = await SpeechToTextModule.fromModelName(
+  models.speech_to_text.whisper_tiny_en(),
+  models.vad.fsmn_vad()
+);
 
 // 1. Configure audio session & permissions
 AudioManager.setAudioSessionOptions({
@@ -150,8 +145,8 @@ To use it, provide the VAD model configuration when loading the module and enabl
 
 ```typescript
 const model = await SpeechToTextModule.fromModelName(
-  WHISPER_TINY_EN,
-  FSMN_VAD // Optional VAD submodule
+  models.speech_to_text.whisper_tiny_en(),
+  models.vad.fsmn_vad()
 );
 
 // Enable VAD logic in the stream context

packages/react-native-executorch/common/rnexecutorch/models/voice_activity_detection/VoiceActivityDetection.cpp

@@ -142,11 +142,16 @@ void VoiceActivityDetection::stream(std::shared_ptr<jsi::Function> callback,
     // Send result to the JS side.
     nativeCallback(speaking);
 
-    std::this_thread::sleep_for(std::chrono::milliseconds(timeout));
+    std::unique_lock<std::mutex> lock(streamCvMutex_);
+    streamCv_.wait_for(lock, std::chrono::milliseconds(timeout),
+                       [this] { return !isStreaming_.load(); });
   }
 }
 
-void VoiceActivityDetection::streamStop() { isStreaming_ = false; }
+void VoiceActivityDetection::streamStop() {
+  isStreaming_ = false;
+  streamCv_.notify_all();
+}
 
 void VoiceActivityDetection::streamInsert(std::span<float> audio) {
   std::scoped_lock lock(audioBufferMutex_);

packages/react-native-executorch/common/rnexecutorch/models/voice_activity_detection/VoiceActivityDetection.h

@@ -1,5 +1,6 @@
 #pragma once
 
+#include <condition_variable>
 #include <cstddef>
 #include <executorch/extension/module/module.h>
 #include <executorch/extension/tensor/tensor.h>
@@ -64,6 +65,8 @@ class VoiceActivityDetection : public BaseModel {
   mutable std::mutex audioBufferMutex_;
   // Streaming state
   std::atomic<bool> isStreaming_ = false;
+  std::condition_variable streamCv_;
+  std::mutex streamCvMutex_;
 };
 
 } // namespace models::voice_activity_detection