Computation of mask indices in Wav2vec2Model fails with low probabilities

[nikvaessen]

Environment info

• transformers version: 4.12.2
• Platform: Linux
• Python version: 3.8
• PyTorch version (GPU?): 1.10

Who can help

@patrickvonplaten

Information

I'm trying to reproduce fine-tuning with Wav2vec2 on Librispeech, however using feature mask probability 0.0012 as in the paper makes the code crash at some point (after ~3_000 steps).

To reproduce

from transformers.models.wav2vec2.modeling_wav2vec2 import _compute_mask_indices

mask = _compute_mask_indices(
    shape=(10, 500),
    mask_prob=0.0012, # or even lower
    mask_length=10,
)

print(mask)

raises

Traceback (most recent call last):
  File "/home/nik/workspace/phd/repo/w2v2-mt-learning/playground/buggy_mask.py", line 3, in <module>
    mask = _compute_mask_indices(
  File "/home/nik/workspace/phd/repo/w2v2-mt-learning/.venv/lib/python3.8/site-packages/transformers/models/wav2vec2/modeling_wav2vec2.py", line 201, in _compute_mask_indices
    dummy_mask_idx = spec_aug_mask_idx[0]
IndexError: index 0 is out of bounds for axis 0 with size 0

Note that using min_mask=1 prevents this issue as well.

Expected behavior

If the probability is so low that no features are masked, the method shouldn't raise an IndexError.