Is24 pr

[shucongzhang]

1. Added the layernorm flag for SummaryMixing
2. Added the code and yamls for SSL
3. Added the yaml for SB 1.0 Conformer
4. Updated readme

[whettenr]

Hi @shucongzhang @TParcollet, I put this question as a comment in pull request 9 but I'm putting it here too just in case.

I had a few questions about the libri-light prep script recipes/Libri-Light/self-supervised-learning/wav2vec2/make_librilight_csv.py.

• for step 2 what do you mean by the vad script ? (im using cut_by_vad.py but there is another vad script)
• also from a brief look at the lengths of the audio files i believe that you could be remove the majority of the data my limiting to only 20.2 seconds, by using the following code. Do you know how many hours are left after this?

def make_csv_for_each(subpath_1_csv_file_folder, max_length=20.2):
    # other code
    if duration_seconds > max_length:
              continue

just to give an estimate, I'm estimating that for the large set you will only have ~100 hours of audio (instead of 51k)