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.

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

Adding Multilingual, Code-Switched, and Hybrid ASR models #7250

Merged
merged 3 commits into from
Aug 17, 2023

Conversation

KunalDhawan
Copy link
Collaborator

What does this PR do ?

This PR:

  1. Adds the multilingual models (stt_multilingual_fastconformer_hybrid_large_pc, stt_multilingual_fastconformer_hybrid_large_pc_blend_eu) to the pre-trained models catalog and ASR docs
  2. Adds the FastConformer Hybrid FR, RU ASR models (stt_ru_fastconformer_hybrid_large_pc, stt_fr_fastconformer_hybrid_large_pc) to the pre-trained models catalog and ASR docs
  3. Adds the code-switching models (stt_enes_conformer_transducer_large_codesw, stt_enes_conformer_ctc_large_codesw) to the ASR docs
  4. Updates the versions of the FastConformer Hybrid ASR models (EN, ES, IT, DE, PL, BY, HR, UA)

Collection: ASR

Changelog

  • Added the FC Hybrid models to nemo/collections/asr/models/hybrid_rnnt_ctc_bpe_models.py
  • Updated the ASR docs at NeMo/docs/source/asr/results.rst
  • Created new results tables for Multilingual (NeMo/docs/source/asr/data/benchmark_multilingual.csv), Code Switching(NeMo/docs/source/asr/data/benchmark_code_switching.csv)

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

Copy link
Collaborator

@nithinraok nithinraok left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@KunalDhawan KunalDhawan merged commit 82d3ee6 into NVIDIA:main Aug 17, 2023
11 checks passed
@KunalDhawan KunalDhawan deleted the add_multilingual_models branch August 17, 2023 20:24
styagi130 pushed a commit to styagi130/NeMo that referenced this pull request Aug 23, 2023
* Updated docs with Hybrid, Multilingual and Code-Swithing ASR models

Signed-off-by: KunalDhawan <[email protected]>

* updated pretrained model list for multilingual models

Signed-off-by: KunalDhawan <[email protected]>

---------

Signed-off-by: KunalDhawan <[email protected]>
Signed-off-by: Siddharth Tyagi <[email protected]>
dorotat-nv pushed a commit to dorotat-nv/NeMo that referenced this pull request Aug 24, 2023
* Updated docs with Hybrid, Multilingual and Code-Swithing ASR models

Signed-off-by: KunalDhawan <[email protected]>

* updated pretrained model list for multilingual models

Signed-off-by: KunalDhawan <[email protected]>

---------

Signed-off-by: KunalDhawan <[email protected]>
Signed-off-by: dorotat <[email protected]>
rohitrango pushed a commit to rohitrango/NeMo that referenced this pull request Jun 25, 2024
* Updated docs with Hybrid, Multilingual and Code-Swithing ASR models

Signed-off-by: KunalDhawan <[email protected]>

* updated pretrained model list for multilingual models

Signed-off-by: KunalDhawan <[email protected]>

---------

Signed-off-by: KunalDhawan <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants