AI NEWS.ccsupertonic-ExecuTorch
This repository hosts the **supertonic** models exported for the React Native ExecuTorch library as ExecuTorch `.pte` programs, ready to run on device. `xnnpack/vector_estimator_xnnpack_int8.pte` and `xnnpack/vocoder_xnnpack_int8.pte` are 8da8w (int8 dynamic activations, int8 per-channel weights) on the Linear layers, with the ConvNeXt pointwise convs moved onto Linears. The int8 set reuses the fp32 duration predictor and text encoder. LibriSpeech test-clean texts, voice F1, 8 steps, WER of a whisper base.en round trip: A backend directory carrying a `NOTES.md` and no `.pte` was exported and not published. Its note records what went wrong.
翻訳準備中のため原文を表示しています
This repository hosts the **supertonic** models exported for the React Native ExecuTorch library as ExecuTorch `.pte` programs, ready to run on device. `xnnpack/vector_estimator_xnnpack_int8.pte` and `xnnpack/vocoder_xnnpack_int8.pte` are 8da8w (int8 dynamic activations, int8 per-channel weights) on the Linear layers, with the ConvNeXt pointwise convs moved onto Linears. The int8 set reuses the fp32 duration predictor and text encoder. LibriSpeech test-clean texts, voice F1, 8 steps, WER of a whisper base.en round trip: A backend directory carrying a `NOTES.md` and no `.pte` was exported and not published. Its note records what went wrong.