[WIP] Discrete unit-based s2st1 recipe for SpeechMatrix Dataset
#5574
Conversation
This file contains 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
# Conflicts: # egs2/speechMatrix/s2st1/run_discrete_unit.sh
Fix text input format and model configuration
Adjust batch_bins to avoid possible OOM
for more information, see https://pre-commit.ci
# Conflicts: # egs2/speechMatrix/s2st1/conf/train_s2st_discrete_unit.yaml # egs2/speechMatrix/s2st1/local/code_hifigan_vocoder.py # egs2/speechMatrix/s2st1/local/generate_waveform_from_code.py # egs2/speechMatrix/s2st1/local/proc_eval_data.py # egs2/speechMatrix/s2st1/local/process_decode_output.py # egs2/speechMatrix/s2st1/local/sm_data_prep.py # egs2/speechMatrix/s2st1/s2st_local.sh # espnet2/bin/s2st_inference.py
Initialize with pretrained weights
for more information, see https://pre-commit.ci
|
This pull request is now in conflict :( |
# Conflicts: # egs2/TEMPLATE/asr1/db.sh
Housekeeping and optimize decoding configs
Full-size training and wav2vec2 + mbart training
for more information, see https://pre-commit.ci
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Outdated suggestions cannot be applied.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?
This PR contributes a discrete unit-based
s2st1recipe for SpeechMatrix Dataset.Why?
Contributing recipe for new dataset (SpeechMatrix) as a deliverable for MIIS capstone project.
MIIS Capstone Team: @tjysdsg @sophia1488 @realzza
ps: currently a draft that has necessary parts ready. We will keep updating this PR as we optimize and test the model.