NVIDIA-NeMo/Speech

NGPU-LM with ONNX model inference

Aperta

#14.501 aperta il 18 ago 2025

 (0 commenti) (0 reazioni) (1 assegnatario)Python (3558 fork)github user discovery
ASRhelp wanted

Metriche repository

Star
 (18.152 stelle)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

How can I perform inference with my ONNX-exported Fast-Conformer model using CTC decoding and NGPU-LM beam search?

Guida contributor