ONNX export of kresnik/wav2vec2-large-xlsr-korean for char-CTC
forced alignment / ASR (wav2vec2 family).
These weights were prepared for the mobile SDK react-native-sherpa-onnx (offline speech tooling for React Native / Android / iOS), including forced-alignment model packs used by the app.
Download and run these on-device models in your pocket — anytime, anywhere — in the mobile app VoiceLab:
| Path | Notes |
|---|---|
onnx/model.onnx |
fp32 |
onnx/model_fp16.onnx |
fp16 weights (when present) |
onnx/model_int8.onnx |
dynamic QUInt8 weight quantization |
vocab.json |
CTC character vocabulary |
config.json |
Transformers model config |
LICENSE |
apache-2.0 |
kresnik/wav2vec2-large-xlsr-korean (apache-2.0)optimum-cli export onnx + onnxruntime dynamic quantization
(export_hf_onnx_pack.py
in the SDK repo)16 kHz mono PCM.
onnx/model.onnx 1.3 GBonnx/model_fp16.onnx 634 MBonnx/model_int8.onnx 356 MB