Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: moonshine and whisper streaming #110

Merged
merged 34 commits into from
Mar 6, 2025
Merged
Show file tree
Hide file tree
Changes from 9 commits
Commits
Show all changes
34 commits
Select commit Hold shift + click to select a range
b216529
moonshine impl
Feb 22, 2025
d9b7712
implemented moonshine on native side, refactored whisper
Feb 25, 2025
e3e73fb
Added Moonshine with KV-cache
Feb 25, 2025
3e7a639
moved resources to ai.swmansion, draft of hook
Feb 27, 2025
d87e132
rebased with fixes, added download progress to s2t controller
Feb 27, 2025
b844873
review changes
Feb 27, 2025
bf60daf
moonshine finished
Mar 3, 2025
f0b374a
changed whisper to 2 modules, implemented useS2T hook, implemented ho…
Mar 3, 2025
b36306c
updated modelUrls.ts
Mar 3, 2025
97feca1
android s2t wip
Mar 4, 2025
382af9a
fixed android side
Mar 4, 2025
19e6426
removed tokenzier files
Mar 4, 2025
075799c
review changes
Mar 4, 2025
d950ad3
yarn.lock
Mar 4, 2025
63502dc
fix to android, s2tcontroller small changes
Mar 5, 2025
f24f00e
fixed android
Mar 5, 2025
a257278
speech-to-text app wip
Mar 5, 2025
8e0ccf7
some more s2t changes
Mar 5, 2025
5ef98e1
remove s2t app
Mar 5, 2025
ea0bc4b
added S2T example app
Mar 5, 2025
ec66581
final cleanup
Mar 5, 2025
0ee1490
cleaned up package.json
Mar 5, 2025
0801c82
hopefully final changes
Mar 6, 2025
b12a0f2
maybe now is final
Mar 6, 2025
893505f
Merge branch 'main' into @mkopcins/moonshine
Mar 6, 2025
c32c589
Podfile.lock
Mar 6, 2025
d9b5893
fixed text display in example app
Mar 6, 2025
ad25811
fixed some more styling on example app
Mar 6, 2025
e395d3a
smallest change of all
Mar 6, 2025
84eab7f
Rename bundle identifiers
chmjkb Mar 6, 2025
949359f
Rename bundle identifiers - v2
chmjkb Mar 6, 2025
e25f498
Update yarn.lock
chmjkb Mar 6, 2025
808562f
Rebuild android dir in demo app
chmjkb Mar 6, 2025
f8db120
checked out computer vision app to main
Mar 6, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 8 additions & 4 deletions examples/computer-vision/App.tsx
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,10 @@ import { View, StyleSheet } from 'react-native';
import { ClassificationScreen } from './screens/ClassificationScreen';
import { ObjectDetectionScreen } from './screens/ObjectDetectionScreen';
import { OCRScreen } from './screens/OCRScreen';
import { SpeechToTextScreen } from './screens/SpeechToTextScreen';

enum ModelType {
SPEECH_TO_TEXT,
STYLE_TRANSFER,
OBJECT_DETECTION,
CLASSIFICATION,
Expand All @@ -23,7 +25,8 @@ export default function App() {
regular: require('./assets/fonts/Aeonik-Regular.otf'),
});
const [selectedMode, setSelectedMode] = useState<ModelType>(
ModelType.STYLE_TRANSFER
ModelType.SPEECH_TO_TEXT
// ModelType.STYLE_TRANSFER
);
const [imageUri, setImageUri] = useState('');

Expand All @@ -33,6 +36,8 @@ export default function App() {

const renderScreen = () => {
switch (selectedMode) {
case ModelType.SPEECH_TO_TEXT:
return <SpeechToTextScreen />;
case ModelType.STYLE_TRANSFER:
return (
<StyleTransferScreen imageUri={imageUri} setImageUri={setImageUri} />
Expand All @@ -51,9 +56,7 @@ export default function App() {
case ModelType.OCR:
return <OCRScreen imageUri={imageUri} setImageUri={setImageUri} />;
default:
return (
<StyleTransferScreen imageUri={imageUri} setImageUri={setImageUri} />
);
return <SpeechToTextScreen />;
}
};

Expand All @@ -65,6 +68,7 @@ export default function App() {
<View style={styles.wheelPickerContainer}>
<ScrollPicker
dataSource={[
'Speech To Text',
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Delete this

'Style Transfer',
'Object Detection',
'Classification',
Expand Down
Loading
Loading