fncode246

batch_size

1

according to table, the batch_size is 3. But what is the segment of each waveform during training? (Is it 3 sec, in this condition what is batch_size?) according to default...

I want to separate a mix sound with separate.py, but the separated sounds are noisy. The mixture was female-male mix and I also test it in evaluate.py, the result was...

using TIMIT data

1

Thank you for your useful code. I can not find WSJ data and want to use "create-speaker-mixtures.zip" to make mixture with TIMIT. How can I use this with TIMIT configuration...

fill empty space

1

There is `fill(value=None, max_words=None)` that: Fills all empty space between segments Is there any way to fill empty space between chunks?

Hello, thanks for sharing useful code. I want to implement "DUAL-PATH RNN: EFFICIENT LONG SEQUENCE MODELING FOR TIME-DOMAIN SINGLE-CHANNEL SPEECH SEPARATION" paper. So I decided to use **DPRNN_base** model instead...

use part of train-clean-100.tar.gz

3

how can i create just 10 hours mix from train-clean-100.tar.gz (instead of 100 h)

how can we fill empty space in S19 file that is less than 4000 bytes and then create new S19 file? the issue is how to write? ``` f =...