Running inference from tensor without pipeline

alibabasglab / MossFormer

This repo provides the processed samples of the manuscript "MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-head Transformer with Convolution-augmented Joint Self-Attentions", which was submitted to ICASSP 2023.

Apache License 2.0

84 stars 7 forks source link

Running inference from tensor without pipeline #3

Closed eitzo closed 2 months ago

eitzo commented 1 year ago

Hi,

how can I run inference on a tensor i.e. using the model directly without the pipeline that takes a wav file as input ?

Thanks in advance

Shirley-0708 commented 2 months ago

Have you found the solution? I have the same issue. Thanks! @eitzo

eitzo commented 2 months ago

No, I ended up just using the pipeline.