NathanLee
NathanLee
Thank you so much. I use squeeze to add one more dim and changed some python code and finally, it works. But I feel it's not faster than before. So...
> what is your pytorch/torchaudio version? Sorry about late check. At that time, my env is below torch 1.7.1+cu101 torchaudio 0.7.2 and python 3.6 Actually I already tried at **torch1.10.0+cu102**...
I think it's same problem with it. https://github.com/wenet-e2e/wenet/issues/1673
Thank you for your explanation. I have one more question. If I use ArcMargin for projection during training, is there a way to determine the optimal number of epochs during...
oh i see. I thought your open c++ code is guranteed. Do you have plan to release official c++ code in the future?
@smallsheep666 I also will check both probs between pytorch and onnx and let you know later. Thank you
I compared output probs from torch(python), Onnx(python) and Onnxruntime(c++) 3 types. I also got same results with @smallsheep666 . Onnx(c++) has problem to get probs. torch(python), Onnx(python) both are showing...
I found an issue that jit model couldn't use reset_states. Then model show difference probs. for example. ``` import sys import torch sys.path.append('/home/silero-vad-master/src/silero_vad') from utils_vad import read_audio from utils_vad import...
oh sorry i missed your model.jit function model.run_method("reset_states"); It works fine for me. Model is reset correctly.
Hi @snakers4 Do you have plan to release jit model half? It means quantized model right?