AudioDec

AudioDec copied to clipboard

Table 4 and 5

1

Excuse me again 1. Table 4 and Table 5 in your paper are about `Latency`. What are the units of the numbers in the table?RTF? 2. There seems to be...

a897456

VCTK dataset

11

Excuse me, may I ask how the training set and validation set of VCTK are divided?

zhanghuiyu123

Is it missing some activation functions between some layers?

6

Thanks for your work. I have trained model in my own dataset. I met same question as [ISSUE7](https://github.com/facebookresearch/AudioDec/issues/7). When I checked the model, I found some difference in AutoEncoder: -...

BridgetteSong

vq_loss increase, not converge

7

I am working on my dataset, whose channels = 2 and sampling rate = 16000. I paste my config file below, the major changes I made are: 1) sample_rate 2)...

lixinghe1999

We all really appreciates you publishing this for research. In terms of using the work, patent rights are not licensed under the current license. Did you apply for one or...

kwinz

Convert AudioDec into a callable Python module

1

Example Usage: https://github.com/voidful/Codec-SUPERB/blob/main/base_codec/audiodec.py

voidful

The test results are different from those in the paper

7

I tested `clean_testset_wav` audio in the Valentini dataset according to the description in your paper. The model used is `vctk_v1`, and the test results are as follows  The test...

WzyCrush