facebookresearch/fairseq

Add pretrained conformer model for the "Wav2Vec 2.0 Large (LV-60 + CV + SWBD + FSH) 960 hours Librispeech" settings

Open

#4,262 opened on Mar 11, 2022

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (6,224 forks)batch import
enhancementhelp wantedneeds triage

Repository metrics

Stars
 (29,107 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

🚀 Feature Request

Add conformer model variant for the "Wav2Vec 2.0 Large (LV-60 + CV + SWBD + FSH) 960 hours Librispeech" settings.

Motivation

Thank you for adding pretrained wav2vec 2.0 conformer model! I see that for the "Wav2Vec 2.0 Large (LV-60 + CV + SWBD + FSH) 960 hours Librispeech" setting, conformer version is still not available. Could you please add it too? Thanks for your help!

Pitch

Add conformer model variant for the "Wav2Vec 2.0 Large (LV-60 + CV + SWBD + FSH) 960 hours Librispeech" settings

Contributor guide

Research direction
Review the existing conformer model configuration for other settings, then adapt it for the Wav2Vec 2.0 Large (LV 60 + CV + SWBD + FSH) 960 hours Librispeech setting, ensuring to update the model architecture, configuration, and any relevant preprocessing scripts.
Tech stack
python
Domain
machine learningai
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorchfairseq
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40