Fast N-Gram LM on GPU + greedy decoding (RNN-T, TDT, CTC) #10989
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
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
Comment on lines
+521
to
+523
| # for i, label in enumerate(labels.tolist()): | ||
| # if label != self._blank_index: | ||
| # batch_lm_states[i] = batch_lm_states_candidates[i][label] |
Check notice
Code scanning / CodeQL
Commented-out code Note
Comment on lines
+586
to
+588
| # for i, label in enumerate(labels.tolist()): | ||
| # if label != self._blank_index: | ||
| # batch_lm_states[i] = batch_lm_states_candidates[i][label] |
Check notice
Code scanning / CodeQL
Commented-out code Note
artbataev
force-pushed
the
gpu_lm_decoding
branch
from
7283fa1 to
442081f
Compare
github-actions
bot
added
core
There was a problem hiding this comment.
CodeQL found more than 20 potential problems in the proposed changes. Check the Files changed tab for more details.
Signed-off-by: Vladimir Bataev <[email protected]>
artbataev
force-pushed
the
gpu_lm_decoding
branch
from
442081f to
0e24533
Compare
github-actions
bot
removed
core
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: artbataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: artbataev <[email protected]>
|
beep boop 🤖: 🙏 The following files have warnings. In case you are familiar with these, please try helping us to improve the code base. Your code was analyzed with PyLint. The following annotations have been identified: Mitigation guide:
By applying these rules, we reduce the occurance of this message in future. Thank you for improving NeMo's documentation! |
|
beep boop 🤖: 🚨 The following files must be fixed before merge! Your code was analyzed with PyLint. The following annotations have been identified: Mitigation guide:
By applying these rules, we reduce the occurance of this message in future. Thank you for improving NeMo's documentation! |
| assert ilabel == -2 | ||
| self.states[from_state]["final"] = ngram["weight"] | ||
| continue | ||
| assert 0 <= ilabel < self.vocab_size |
Check warning
Code scanning / CodeQL
Redundant comparison Warning
|
This PR is stale because it has been open for 14 days with no activity. Remove stale label or comment or update or this will be closed in 7 days. |
Signed-off-by: Vladimir Bataev <[email protected]>
| from collections.abc import Iterator | ||
| from dataclasses import InitVar, dataclass, field | ||
| from pathlib import Path | ||
| from typing import List, NamedTuple, Optional, cast |
Check notice
Code scanning / CodeQL
Unused import Note
| from tqdm.auto import tqdm | ||
|
|
||
| from nemo.collections.common.parts import NEG_INF | ||
| from nemo.core import ModelPT, PretrainedModelInfo |
Check notice
Code scanning / CodeQL
Unused import Note
|
|
||
| self._final_resolved = False | ||
|
|
||
| def list_available_models(cls): |
Check notice
Code scanning / CodeQL
First parameter of a method is not named 'self' Note
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: artbataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Comment on lines
+40
to
+43
| from nemo.collections.asr.parts.submodules.ngram_lm_triton import ( | ||
| _ngram_advance_triton_kernel, | ||
| _ngram_advance_triton_kernel_v2, | ||
| ) |
Check notice
Code scanning / CodeQL
Unused import Note
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
Signed-off-by: Vladimir Bataev <[email protected]>
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 ?
Add a one line overview of what this PR aims to accomplish.
Collection: [Note which collection this PR will affect]
Changelog
Usage
Step 1: Build LM for ASR Model (model-dependent) on domain texts
python nemo/scripts/asr_language_modeling/ngram_lm/train_kenlm.py \ nemo_model_file="nvidia/parakeet-rnnt-1.1b" \ train_paths=["<train_manifest>"] \ kenlm_bin_path=$KENLM_BIN_PATH \ kenlm_model_file=parakeet-rnnt-1.1b_lm-o6.arpa \ ngram_length=6 \ preserve_arpa=trueStep 2: Run Decoding with LM (arpa)
GitHub Actions CI
The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.
The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".
Before your PR is "Ready for review"
Pre checks:
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information