v0.5.6

What's Changed

• fix: s2t demo app crashes by @jakmro in #611
• chore: bump version to v0.5.6 by @jakmro in #618

Full Changelog: v0.5.5...v0.5.6

v0.5.5

What's Changed

• bump 0.5.4 by @mkopcins in #593
• V0.5.5 by @jakmro in #602

Full Changelog: v0.5.4...v0.5.5

v0.5.4

What's Changed

• Improvements to Speech to text pipeline (migrated typescipt code to cpp)

Full Changelog: v0.5.3...v0.5.4

v0.5.3

What's Changed

• Fix to LLMs android performance. Before 0.5.3 LLMs api was written native code and did not support model instantiation. With this fix we are migrating to cpp code with JSI while maintaining performace for LLMs while allowing to load multiple models at the same time.
• Fix to react-native-executorch not working on iPads
  Full Changelog: v0.5.2...v0.5.3

v0.5.2

What's Changed

• v0.5.2 by @mlodyjesienin in #568

Full Changelog: v0.5.1...v0.5.2

v0.5.1

What's Changed

• v0.5.1 by @chmjkb in #531

Full Changelog: v0.5.0...v0.5.1

v0.5.0 🚀

Announcing React Native ExecuTorch v0.5.0 ⚛️

What’s new?

🏎️ A full native code rewrite based on C++ JSI bindings enabling zero-copy data transfer between native code and JS
🔥 Up to 2x faster Whisper transcription on iOS
📷 CLIP - extract semantic meaning of images
🚴 Significant improvements to the performance of text embeddings
🧘 Rewrite of the STT streaming API delivering better qualitative results & DX
🐐 Specify LLM structured output schemas using zod
👌 LLMs now correctly handle Unicode/emoji in outputs

⚠️ Breaking changes

• Multiple model instances: JSI bindings remove the static singleton limitation. You can now create and run multiple instances of the same model simultaneously.
• We've replaced separate URL imports with bundled model objects. Instead of manually specifying modelSource, tokenizerSource, and tokenizerConfigSource, just pass a single object like LLAMA_3_2_1B. The individual URLs are still accessible as properties if you need them.

import {
  useLLM,
  LLAMA3_2_1B,
} from 'react-native-executorch';

// Current API:
const llm = useLLM({ model: LLAMA3_2_1B });

// Previous API:
const llama = useLLM({
  modelSource: LLAMA3_2_1B,
  tokenizerSource: LLAMA3_2_TOKENIZER,
  tokenizerConfigSource: LLAMA3_2_TOKENIZER_CONFIG,
});

v0.4.8

What's Changed

• fix: Executorchmodule BigInt64Array handling by @jakmro in #470
• fix: error messages formatting by @jakmro in #476

Full Changelog: v0.4.7...v0.4.8

v0.4.7

What's Changed

• chore: update aar path to point to branch instead of release by @NorbertKlockiewicz in #441

Full Changelog: v0.4.6...v0.4.7

v0.4.6

Full Changelog: v0.4.5...v0.4.6

• Changed version of executorch.aar to point to a specific release