Modelpublic

OpenVoiceOS/inesc-id-ebranch-w2vbert2-ep-aed-onnx

sourceHugging Facecc-by-4.0updated 2mo agoView on Hugging Face

0likes15downloads

Model Card

EBranch-w2vBERT2-EP (attention decoder) — ONNX

ONNX export of inesc-id/EBranch-w2vBERT2-EP (ESPnet2 E-Branchformer with a w2v-BERT 2.0 frontend, trained on ~425 h of European Portuguese from the CAMOES project) for onnx-asr with the espnet-aed model type (requires the espnet model-family patches, see TigreGotico/onnx-asr PR #4).

This repo holds the full-model AED variant: encoder plus transformer attention decoder with greedy decoding. Best quality; adds a ~127 MB (40 MB int8) decoder.

The original model uses partial rotary position embeddings (dim=32 of 64, interleaved pairs, self-attention only); the rotary frequency table is taken verbatim from the released checkpoint. fp32 CTC output is bit-exact with the original PyTorch model (8/8 test clips identical). fp32 and int8-quantized graphs are included.

Usage

python

import onnx_asr
model = onnx_asr.load_model("espnet-aed", "path/to/this/repo")  # or quantization="int8"
print(model.recognize("audio_16khz.wav"))

License: CC-BY-4.0 (inherited from the source model; attribution: INESC-ID, CAMOES project, arXiv:2508.19721).