chore: switch to fp16 CoreML whisper models (#1224)

Updates Whisper models URLs to match the recently uploaded CoreML fp16
models.

The newly uploaded fp16 models are roughly 50% reduced in size and ~30%
faster than the old fp32 ones.

- [ ] Yes
- [x] No

- [ ] Bug fix (change which fixes an issue)
- [ ] New feature (change which adds functionality)
- [ ] Documentation update (improves or adds clarity to existing
documentation)
- [x] Other (chores, tests, code style improvements etc.)

- [x] iOS
- [ ] Android

<!-- Provide step-by-step instructions on how to test your changes.
Include setup details if necessary. -->

<!-- Add screenshots here, if applicable -->

<!-- Link related issues here using #issue-number -->

- [x] I have performed a self-review of my code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have updated the documentation accordingly
- [x] My changes generate no new warnings

<!-- Include any additional information, assumptions, or context that
reviewers might need to understand this PR. -->

Author: IgorSwat

apps/speech/screens/SpeechToTextScreen.tsx

@@ -22,12 +22,24 @@ import { ModelPicker, ModelOption } from '../components/ModelPicker';
 const speechToText = models.speech_to_text;
 const vad = models.vad;
 
+const isSimulator = DeviceInfo.isEmulatorSync();
+const backend = Platform.OS === 'ios' && !isSimulator ? 'coreml' : 'xnnpack';
+
 type STTModelSources = SpeechToTextProps['model'];
 
 const MODELS: ModelOption<STTModelSources>[] = [
-  { label: 'Whisper Tiny EN', value: speechToText.whisper_tiny_en() },
-  { label: 'Whisper Base EN', value: speechToText.whisper_base_en() },
-  { label: 'Whisper Small EN', value: speechToText.whisper_small_en() },
+  {
+    label: 'Whisper Tiny EN',
+    value: speechToText.whisper_tiny_en({ backend }),
+  },
+  {
+    label: 'Whisper Base EN',
+    value: speechToText.whisper_base_en({ backend }),
+  },
+  {
+    label: 'Whisper Small EN',
+    value: speechToText.whisper_small_en({ backend }),
+  },
 ];
 import FontAwesome from '@expo/vector-icons/FontAwesome';
 import {
@@ -42,12 +54,10 @@ import DeviceInfo from 'react-native-device-info';
 import { VerboseTranscription } from '../components/VerboseTranscription';
 import ErrorBanner from '../components/ErrorBanner';
 
-const isSimulator = DeviceInfo.isEmulatorSync();
-
 export const SpeechToTextScreen = ({ onBack }: { onBack: () => void }) => {
   const [selectedModel, setSelectedModel] = useState<STTModelSources>(
-    Platform.OS === 'ios'
-      ? speechToText.whisper_base_en()
+    Platform.OS === 'ios' && !isSimulator
+      ? speechToText.whisper_base_en({ backend })
       : speechToText.whisper_tiny_en()
   );
 

packages/react-native-executorch/src/constants/modelUrls.ts

@@ -816,27 +816,27 @@ export const STYLE_TRANSFER_UDNIE_QUANTIZED = {
 // S2T
 export const WHISPER_TINY_EN_TOKENIZER = `${URL_PREFIX}-whisper-tiny.en/${VERSION_TAG}/tokenizer.json`;
 export const WHISPER_TINY_EN_MODEL_XNNPACK = `${URL_PREFIX}-whisper-tiny.en/${VERSION_TAG}/xnnpack/whisper_tiny_en_xnnpack_fp32.pte`;
-export const WHISPER_TINY_EN_MODEL_COREML = `${URL_PREFIX}-whisper-tiny.en/${VERSION_TAG}/coreml/whisper_tiny_en_coreml_fp32.pte`;
+export const WHISPER_TINY_EN_MODEL_COREML = `${URL_PREFIX}-whisper-tiny.en/${VERSION_TAG}/coreml/whisper_tiny_en_coreml_fp16.pte`;
 
 export const WHISPER_BASE_EN_TOKENIZER = `${URL_PREFIX}-whisper-base.en/${VERSION_TAG}/tokenizer.json`;
 export const WHISPER_BASE_EN_MODEL_XNNPACK = `${URL_PREFIX}-whisper-base.en/${VERSION_TAG}/xnnpack/whisper_base_en_xnnpack_fp32.pte`;
-export const WHISPER_BASE_EN_MODEL_COREML = `${URL_PREFIX}-whisper-base.en/${VERSION_TAG}/coreml/whisper_base_en_coreml_fp32.pte`;
+export const WHISPER_BASE_EN_MODEL_COREML = `${URL_PREFIX}-whisper-base.en/${VERSION_TAG}/coreml/whisper_base_en_coreml_fp16.pte`;
 
 export const WHISPER_SMALL_EN_TOKENIZER = `${URL_PREFIX}-whisper-small.en/${VERSION_TAG}/tokenizer.json`;
 export const WHISPER_SMALL_EN_MODEL_XNNPACK = `${URL_PREFIX}-whisper-small.en/${VERSION_TAG}/xnnpack/whisper_small_en_xnnpack_fp32.pte`;
-export const WHISPER_SMALL_EN_MODEL_COREML = `${URL_PREFIX}-whisper-small.en/${VERSION_TAG}/coreml/whisper_small_en_coreml_fp32.pte`;
+export const WHISPER_SMALL_EN_MODEL_COREML = `${URL_PREFIX}-whisper-small.en/${VERSION_TAG}/coreml/whisper_small_en_coreml_fp16.pte`;
 
 export const WHISPER_TINY_TOKENIZER = `${URL_PREFIX}-whisper-tiny/${VERSION_TAG}/tokenizer.json`;
 export const WHISPER_TINY_MODEL_XNNPACK = `${URL_PREFIX}-whisper-tiny/${VERSION_TAG}/xnnpack/whisper_tiny_xnnpack_fp32.pte`;
-export const WHISPER_TINY_MODEL_COREML = `${URL_PREFIX}-whisper-tiny/${VERSION_TAG}/coreml/whisper_tiny_coreml_fp32.pte`;
+export const WHISPER_TINY_MODEL_COREML = `${URL_PREFIX}-whisper-tiny/${VERSION_TAG}/coreml/whisper_tiny_coreml_fp16.pte`;
 
 export const WHISPER_BASE_TOKENIZER = `${URL_PREFIX}-whisper-base/${VERSION_TAG}/tokenizer.json`;
 export const WHISPER_BASE_MODEL_XNNPACK = `${URL_PREFIX}-whisper-base/${VERSION_TAG}/xnnpack/whisper_base_xnnpack_fp32.pte`;
-export const WHISPER_BASE_MODEL_COREML = `${URL_PREFIX}-whisper-base/${VERSION_TAG}/coreml/whisper_base_coreml_fp32.pte`;
+export const WHISPER_BASE_MODEL_COREML = `${URL_PREFIX}-whisper-base/${VERSION_TAG}/coreml/whisper_base_coreml_fp16.pte`;
 
 export const WHISPER_SMALL_TOKENIZER = `${URL_PREFIX}-whisper-small/${VERSION_TAG}/tokenizer.json`;
 export const WHISPER_SMALL_MODEL_XNNPACK = `${URL_PREFIX}-whisper-small/${VERSION_TAG}/xnnpack/whisper_small_xnnpack_fp32.pte`;
-export const WHISPER_SMALL_MODEL_COREML = `${URL_PREFIX}-whisper-small/${VERSION_TAG}/coreml/whisper_small_coreml_fp32.pte`;
+export const WHISPER_SMALL_MODEL_COREML = `${URL_PREFIX}-whisper-small/${VERSION_TAG}/coreml/whisper_small_coreml_fp16.pte`;
 
 /**
  * @category Models - Speech To Text