fix partial audio transcription order: #10379

nithinraok · 2024-09-06T20:21:37Z

What does this PR do ?

Removes special case of sorting for EncDecMultiTaskModels
Removes partial audio transcription for all Model Types
Now transcribe_speech.py transcribes as per presence of offset and duration in manifest automatically without special conditions
Adds support to transcriptionmixin to read manifest for transcribing on high level rather than subclasses to deal with it
Merges NeMo 2.0 transcription usage for all Model Types

Collection: ASR

Usage

python transcribe_speech.py model_path=<.nemo file> dataset_manifest=<manifest_file>

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The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.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:

Make sure you read and followed Contributor guidelines
Did you write any new necessary tests?
Did you add or update any necessary documentation?
Does the PR affect components that are optional to install? (Ex: Numba, Pynini, Apex etc)
- Reviewer: Does the PR have correct import guards for all optional libraries?

PR Type:

New Feature
Bugfix
Documentation

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

Related to # (issue)

pzelasko · 2024-09-09T19:05:53Z

wouldn't it be better to enable pre-sorting for partial audio instead (if possible)?

nithinraok · 2024-09-09T23:39:44Z

Thanks for the suggestion @pzelasko, that needs a whole revamp and done that.
But now I notice we can unify partial audio.

~~Canary can perform partial audio transcription when offset provided through manifest (previous assumption was no I believe looking at the code)~~ -> Fixed to allow partial transcribe to be done using transcribe by default
~~If 1, then we can add additional support for .transcribe() for ASR Models to support reading from manifest. Currently TranscriptioMixin supports audio, list of audio, dataloader.~~ Added support for manifest file reading to TranscribeMixIn high level

Signed-off-by: Nithin Rao Koluguri <nithinraok>

Signed-off-by: nithinraok <nithinraok@users.noreply.github.com>

Signed-off-by: Nithin Rao Koluguri <nithinraok>

Signed-off-by: nithinraok <nithinraok@users.noreply.github.com>

Signed-off-by: Nithin Rao Koluguri <nithinraok>

nemo/collections/multimodal/data/neva/neva_energon_dataset.py

nemo/collections/vlm/neva/data/conversation.py

nemo/lightning/resume.py

tests/collections/llm/recipes/test_llama3_70b.py

Signed-off-by: Nithin Rao Koluguri <nithinraok>

Signed-off-by: nithinraok <nithinraok@users.noreply.github.com>

examples/asr/transcribe_speech.py

nemo/collections/asr/models/aed_multitask_models.py

nemo/collections/asr/parts/utils/transcribe_utils.py

Signed-off-by: Nithin Rao Koluguri <nithinraok>

titu1994

Requires minor changes, but overall nice cleanup of partial transcription

titu1994 · 2024-09-11T21:11:56Z

examples/asr/transcribe_speech.py

@@ -293,7 +284,7 @@ def main(cfg: TranscriptionConfig) -> Union[TranscriptionConfig, List[Hypothesis
    elif isinstance(asr_model, EncDecHybridRNNTCTCModel):
        if cfg.decoder_type and cfg.decoder_type not in ['ctc', 'rnnt']:
            raise ValueError('Hybrid model only support ctc or rnnt decoding!')
-    else:  # rnnt model, there could be other models needs to be addressed.


Add a else case in case there's a future model type

titu1994 · 2024-09-11T21:12:21Z

examples/asr/transcribe_speech.py

-        filepaths, partial_audio = prepare_audio_data(cfg)
+    filepaths, sorted_manifest_path = prepare_audio_data(cfg)
+
+    remove_path_after_done = sorted_manifest_path if sorted_manifest_path is not None else None


What does this flag calculate ?

This was added previously to clean the temporarily created manifest later.

titu1994 · 2024-09-11T21:13:17Z

nemo/collections/asr/models/aed_multitask_models.py

@@ -783,17 +783,6 @@ def _transcribe_on_begin(self, audio, trcfg: MultiTaskTranscriptionConfig):
                    trcfg._internal.primary_language = self.tokenizer.langs[0]
                    logging.debug(f"Transcribing with default setting of {trcfg._internal.primary_language}.")

-        elif isinstance(audio, str):


Why are we removing manifest ability from multi task model ?

its not removing but same check is now already part of TranscriptionMixin to handle manifest

titu1994 · 2024-09-11T21:14:50Z

nemo/collections/asr/models/aed_multitask_models.py

+            manifest_filepath = config['manifest_filepath']
+            batch_size = config['batch_size']
+        else:
+            manifest_filepath = os.path.join(config['temp_dir'], 'manifest.json')


When is this else case occuring? Can you add a comment ?

This is from the Transcription mixin where temp_dir was created to create a temp manifest when audio files are passed through list to .transcribe(). Added comment!

titu1994 · 2024-09-11T21:16:36Z

nemo/collections/asr/parts/mixins/transcription.py

@@ -480,6 +481,12 @@ def _transcribe_input_processing(self, audio, trcfg: TranscribeConfig):

        # Check if audio is a list of strings (filepaths or manifests)
        if isinstance(audio[0], str):
+            trcfg._internal.manifest_filepath = None


You need to add this argument to the internal config of transcribe above

Done, thank you!

Signed-off-by: Nithin Rao Koluguri <nithinraok>

Signed-off-by: nithinraok <nithinraok@users.noreply.github.com>

stevehuang52

Looks good on my end, thanks~!

* fix partial audio transcription order: Signed-off-by: Nithin Rao Koluguri <nithinraok> * update transcribe_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * fix canary transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * for filepaths Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * add override config option Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * clean up Signed-off-by: stevehuang52 <heh@nvidia.com> * completely remove partial audio transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * update doc strings Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * support for translate_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * suggested changes from som Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com>

* fix partial audio transcription order: Signed-off-by: Nithin Rao Koluguri <nithinraok> * update transcribe_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * fix canary transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * for filepaths Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * add override config option Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * clean up Signed-off-by: stevehuang52 <heh@nvidia.com> * completely remove partial audio transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * update doc strings Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * support for translate_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * suggested changes from som Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com> Signed-off-by: George Armstrong <georgea@nvidia.com>

* add parakeet-tdt_ctc-110m model (#10461) * add parakeet-tdt_ctc-110m model Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> * fix partial audio transcription order: (#10379) * fix partial audio transcription order: Signed-off-by: Nithin Rao Koluguri <nithinraok> * update transcribe_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * fix canary transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * for filepaths Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * add override config option Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * clean up Signed-off-by: stevehuang52 <heh@nvidia.com> * completely remove partial audio transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * update doc strings Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * support for translate_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * suggested changes from som Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com>

* add parakeet-tdt_ctc-110m model (#10461) * add parakeet-tdt_ctc-110m model Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> * fix partial audio transcription order: (#10379) * fix partial audio transcription order: Signed-off-by: Nithin Rao Koluguri <nithinraok> * update transcribe_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * fix canary transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * for filepaths Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * add override config option Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * clean up Signed-off-by: stevehuang52 <heh@nvidia.com> * completely remove partial audio transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * update doc strings Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * support for translate_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * suggested changes from som Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com> Signed-off-by: Alexandros Koumparoulis <akoumparouli@nvidia.com>

* fix partial audio transcription order: Signed-off-by: Nithin Rao Koluguri <nithinraok> * update transcribe_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * fix canary transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * for filepaths Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * add override config option Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * clean up Signed-off-by: stevehuang52 <heh@nvidia.com> * completely remove partial audio transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * update doc strings Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * support for translate_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * suggested changes from som Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com>

* fix partial audio transcription order: Signed-off-by: Nithin Rao Koluguri <nithinraok> * update transcribe_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * fix canary transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * for filepaths Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * add override config option Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * clean up Signed-off-by: stevehuang52 <heh@nvidia.com> * completely remove partial audio transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * update doc strings Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * support for translate_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * suggested changes from som Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com> Signed-off-by: Lifu Zhang <tomzhanglf@gmail.com>

* fix partial audio transcription order: Signed-off-by: Nithin Rao Koluguri <nithinraok> * update transcribe_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * fix canary transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * for filepaths Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * add override config option Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * clean up Signed-off-by: stevehuang52 <heh@nvidia.com> * completely remove partial audio transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * update doc strings Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * support for translate_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * suggested changes from som Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com> Signed-off-by: Hainan Xu <hainanx@nvidia.com>

* fix partial audio transcription order: Signed-off-by: Nithin Rao Koluguri <nithinraok> * update transcribe_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * fix canary transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * for filepaths Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * add override config option Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * clean up Signed-off-by: stevehuang52 <heh@nvidia.com> * completely remove partial audio transcription Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> * update doc strings Signed-off-by: Nithin Rao Koluguri <nithinraok> * remove unused imports Signed-off-by: Nithin Rao Koluguri <nithinraok> * support for translate_speech.py Signed-off-by: Nithin Rao Koluguri <nithinraok> * suggested changes from som Signed-off-by: Nithin Rao Koluguri <nithinraok> * Apply isort and black reformatting Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> --------- Signed-off-by: Nithin Rao Koluguri <nithinraok> Signed-off-by: nithinraok <nithinraok@users.noreply.github.com> Signed-off-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Nithin Rao Koluguri <nithinraok> Co-authored-by: nithinraok <nithinraok@users.noreply.github.com> Co-authored-by: stevehuang52 <heh@nvidia.com> Co-authored-by: Pablo Garay <palenq@gmail.com>

github-actions bot added the ASR label Sep 6, 2024

nithinraok requested review from pzelasko and titu1994 September 6, 2024 20:22

nithinraok added the Run CICD label Sep 6, 2024

nithinraok added Run CICD and removed Run CICD labels Sep 9, 2024

Nithin Rao Koluguri and others added 8 commits September 10, 2024 06:18

fix partial audio transcription order:

e8ce673

Signed-off-by: Nithin Rao Koluguri <nithinraok>

update transcribe_speech.py

a906140

Signed-off-by: Nithin Rao Koluguri <nithinraok>

fix canary transcription

66d39d5

Signed-off-by: Nithin Rao Koluguri <nithinraok>

Apply isort and black reformatting

b7ba4c2

Signed-off-by: nithinraok <nithinraok@users.noreply.github.com>

Apply isort and black reformatting

cc4db7f

Signed-off-by: nithinraok <nithinraok@users.noreply.github.com>

for filepaths

d837faa

Signed-off-by: Nithin Rao Koluguri <nithinraok>

Apply isort and black reformatting

18c679a

Signed-off-by: nithinraok <nithinraok@users.noreply.github.com>

add override config option

6dd2f46

Signed-off-by: Nithin Rao Koluguri <nithinraok>

nithinraok requested review from pablo-garay and ko3n1g as code owners September 10, 2024 13:20

github-actions bot added NLP CI common Multi Modal labels Sep 10, 2024

github-advanced-security bot found potential problems Sep 10, 2024

View reviewed changes

nithinraok force-pushed the fix_partial_audio_transcription branch from 014a6d2 to 6dd2f46 Compare September 10, 2024 13:38

github-actions bot removed NLP CI common Multi Modal labels Sep 10, 2024

nithinraok added the Run CICD label Sep 10, 2024

completely remove partial audio transcription

43c2bc1

Signed-off-by: Nithin Rao Koluguri <nithinraok>

github-actions bot added the Multi Modal label Sep 10, 2024

Apply isort and black reformatting

00ce9ad

Signed-off-by: nithinraok <nithinraok@users.noreply.github.com>

github-advanced-security bot found potential problems Sep 10, 2024

View reviewed changes

examples/asr/transcribe_speech.py Fixed Show fixed Hide fixed

nemo/collections/asr/models/aed_multitask_models.py Fixed Show fixed Hide fixed

nemo/collections/asr/parts/utils/transcribe_utils.py Fixed Show fixed Hide fixed

Nithin Rao Koluguri added 2 commits September 10, 2024 11:26

update doc strings

f32c5dd

Signed-off-by: Nithin Rao Koluguri <nithinraok>

remove unused imports

2986988

Signed-off-by: Nithin Rao Koluguri <nithinraok>

nithinraok added Run CICD and removed Run CICD labels Sep 10, 2024

support for translate_speech.py

29cdfa1

Signed-off-by: Nithin Rao Koluguri <nithinraok>

titu1994 reviewed Sep 11, 2024

View reviewed changes

Nithin Rao Koluguri and others added 2 commits September 11, 2024 14:36

suggested changes from som

2ee3422

Signed-off-by: Nithin Rao Koluguri <nithinraok>

Apply isort and black reformatting

93d5883

Signed-off-by: nithinraok <nithinraok@users.noreply.github.com>

nithinraok added Run CICD and removed Run CICD labels Sep 11, 2024

Merge branch 'main' into fix_partial_audio_transcription

32142c0

pablo-garay added Run CICD and removed Run CICD labels Sep 12, 2024

stevehuang52 approved these changes Sep 16, 2024

View reviewed changes

nithinraok merged commit a250726 into main Sep 16, 2024
149 of 156 checks passed

nithinraok deleted the fix_partial_audio_transcription branch September 16, 2024 17:01

nithinraok mentioned this pull request Sep 17, 2024

Cherry pick 10379 and 10461 #10510

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

fix partial audio transcription order: #10379

fix partial audio transcription order: #10379

nithinraok commented Sep 6, 2024 •

edited

Loading

pzelasko commented Sep 9, 2024

nithinraok commented Sep 9, 2024 •

edited

Loading

titu1994 left a comment

titu1994 Sep 11, 2024

titu1994 Sep 11, 2024

nithinraok Sep 11, 2024

titu1994 Sep 11, 2024

nithinraok Sep 11, 2024

titu1994 Sep 11, 2024

nithinraok Sep 11, 2024 •

edited

Loading

titu1994 Sep 11, 2024

nithinraok Sep 11, 2024

stevehuang52 left a comment

fix partial audio transcription order: #10379

fix partial audio transcription order: #10379

Conversation

nithinraok commented Sep 6, 2024 • edited Loading

What does this PR do ?

Usage

GitHub Actions CI

Before your PR is "Ready for review"

Who can review?

Additional Information

pzelasko commented Sep 9, 2024

nithinraok commented Sep 9, 2024 • edited Loading

titu1994 left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

nithinraok Sep 11, 2024 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

stevehuang52 left a comment

Choose a reason for hiding this comment

nithinraok commented Sep 6, 2024 •

edited

Loading

nithinraok commented Sep 9, 2024 •

edited

Loading

nithinraok Sep 11, 2024 •

edited

Loading