Add BestRQ pretraining #873
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
facebook-github-bot
added
the
CLA Signed
iamyuanchung
requested changes
Jan 27, 2025
| @final | ||
| @dataclass | ||
| class BestRQOutput: | ||
| """Holds the output of a w2v-BERT model.""" |
| @final | ||
| @dataclass | ||
| class BestRQLoss: | ||
| """Holds the loss of a w2v-BERT model.""" |
| spatial_span_len: int = 10, | ||
| max_spatial_mask_prob: float = 0.0, | ||
| min_num_spatial_mask_spans: int = 2, | ||
| mask_overlap_strategy: str = "no", # remove_masks (fs2 default), add_masks_jc (additive, v1), add_masks_mike (additive, v2), roll (Alex's suggestion) |
There was a problem hiding this comment.
The comment here is not useful for people outside of Arrival. Could you add more descriptions on what each strategy does?
| spatial_mask_span_len: int = 10 | ||
| """The length of each spatial mask span that is applied over features.""" | ||
|
|
||
| max_spatial_mask_prob: float = 0.0 |
There was a problem hiding this comment.
Can you add "Best-RQ does not have spatial masking during pre-training, and spatial masking is only used optionally during ASR fine-tuning to mimic SpecAugment."?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do? Please describe:
This is a draft implementation of the BestRQ algorithm from https://arxiv.org/pdf/2202.01855
Fixes #{issue number}
Does your PR introduce any breaking changes? If yes, please list them:
List of all backwards-incompatible changes.
Check list: