Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[WIP] Add phone based train and decode for gigaspeech #1023

Open
wants to merge 8 commits into
base: master
Choose a base branch
from
Open

[WIP] Add phone based train and decode for gigaspeech #1023

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
9cbe547
Add phone based train and decode for gigaspeech
Apr 26, 2023
c6b4159
Update type hint
Apr 26, 2023
0b5996b
Fix comments
Apr 26, 2023
23a9b66
Fix type hint
Apr 26, 2023
5e7e1a3
Fit type hint
Apr 26, 2023
ce33bf4
Fix for style check
Apr 27, 2023
984f807
Merge branch 'k2-fsa:master' into phone
yfyeung May 4, 2023
4858e2b
Merge branch 'k2-fsa:master' into phone
yfyeung Apr 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 3 additions & 7 deletions egs/gigaspeech/ASR/pruned_transducer_stateless2/asr_datamodule.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -389,16 +389,14 @@ def test_dataloaders(self, cuts: CutSet) -> DataLoader:
@lru_cache()
def train_cuts(self) -> CutSet:
logging.info(f"About to get train_{self.args.subset} cuts")
path = self.args.manifest_dir / f"gigaspeech_cuts_{self.args.subset}.jsonl.gz"
path = self.args.manifest_dir / f"cuts_{self.args.subset}.jsonl.gz"
cuts_train = CutSet.from_jsonl_lazy(path)
return cuts_train

@lru_cache()
def dev_cuts(self) -> CutSet:
logging.info("About to get dev cuts")
cuts_valid = load_manifest_lazy(
self.args.manifest_dir / "gigaspeech_cuts_DEV.jsonl.gz"
)
cuts_valid = load_manifest_lazy(self.args.manifest_dir / "cuts_DEV.jsonl.gz")
if self.args.small_dev:
return cuts_valid.subset(first=1000)
else:
Expand All @@ -407,6 +405,4 @@ def dev_cuts(self) -> CutSet:
@lru_cache()
def test_cuts(self) -> CutSet:
logging.info("About to get test cuts")
return load_manifest_lazy(
self.args.manifest_dir / "gigaspeech_cuts_TEST.jsonl.gz"
)
return load_manifest_lazy(self.args.manifest_dir / "cuts_TEST.jsonl.gz")
Loading
Loading