react-native-executorch-whisper-tiny
This repository hosts the **whisper-tiny** models exported for the React Native ExecuTorch library as ExecuTorch `.pte` programs, ready to run on device. `xnnpack/whisper_tiny_xnnpack_int8.pte` is 8da8w (int8 dynamic activations, int8 per-channel weights). Greedy WER (CER for zh) against the fp32 file, LibriSpeech test-clean (150 clips) and FLEURS (80 per language): These files are published for the **ExecuTorch v1.4.1** runtime. ExecuTorch gives no forward compatibility guarantee, so an older runtime may fail to load them.
This repository hosts the **whisper-tiny** models exported for the React Native ExecuTorch library as ExecuTorch `.pte` programs, ready to run on device. `xnnpack/whisper_tiny_xnnpack_int8.pte` is 8da8w (int8 dynamic activations, int8 per-channel weights). Greedy WER (CER for zh) against the fp32 file, LibriSpeech test-clean (150 clips) and FLEURS (80 per language): These files are published for the **ExecuTorch v1.4.1** runtime. ExecuTorch gives no forward compatibility guarantee, so an older runtime may fail to load them.
AI NEWS.cc