STT/ASR - onnx
Collection
OVOS STT/ASR models for onnx-asr (ONNX runtime). Most ship fp32 + int8 (set quantization: int8 for faster/smaller CPU inference). • 175 items • Updated • 2
EBranch-w2vBERT2-EP (CTC head) — 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-ctc model type (requires the espnet model-family patches, see
TigreGotico/onnx-asr PR #4).
This repo holds the CTC variant: a single graph ending in the auxiliary CTC head with greedy decoding. Smaller and faster; slightly worse WER than the AED variant.
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
import onnx_asr
model = onnx_asr.load_model("espnet-ctc", "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).
- Downloads last month
- -
Model tree for OpenVoiceOS/inesc-id-ebranch-w2vbert2-ep-ctc-onnx
Base model
inesc-id/EBranch-w2vBERT2-EP