Downsampling #1888
Merged
Downsampling #1888
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
TParcollet
requested changes
Mar 23, 2023
Collaborator
TParcollet
left a comment
There was a problem hiding this comment.
Thanks! See my comments.
recipes/LibriSpeech/ASR/CTC/hparams/downsampled/train_hf_wavlm_average_downsampling.yaml
Outdated
Show resolved
Hide resolved
anautsch
reviewed
Mar 23, 2023
Quick fix.
Adel-Moumen
reviewed
Mar 24, 2023
| from speechbrain.utils.distributed import run_on_main | ||
| from hyperpyyaml import load_hyperpyyaml | ||
| from pathlib import Path | ||
| from pyctcdecode import build_ctcdecoder |
Collaborator
There was a problem hiding this comment.
it should be optional nop? Now this is mandatory to pip install pyctcdecode in order to use the CTC wav2vec...
Collaborator
Author
There was a problem hiding this comment.
Yes it should be optional, will put the import later
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
Code for the best technique in the paper "Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study" : https://arxiv.org/abs/2303.06740, allowing for sequence downsampling during fine-tuning of SSL models. This leads to lower inference times with low performance drops.