GithubHelp home page GithubHelp logo

raghuch / saber Goto Github PK

View Code? Open in Web Editor NEW

This project forked from saber-labs/saber

0.0 1.0 0.0 2.81 MB

Semi-Supervised Audio Baseline for Easy Reproduction

License: MIT License

Jupyter Notebook 91.67% Shell 0.32% Python 8.02%

saber's Introduction

alt text SABER - Semi-Supervised Audio Baseline for Easy Reproduction

A PyTorch project currently under research can provide easily reproducible baselines for automatic speech recognition using semi-supervised learning. Contributions are welcome.

Overview

SABER consists of the following components

  • Several SOTA models including an Mixnet based variant of QuartzNet by NVIDIA.
  • Ranger (RAdam + Lookahead) optimizer to offset warmup used by SpecAugment (by Leslie Smith)
  • Mish activation function
  • Data Augmentions used are SpecNoise, SpecAugment, SpecSparkle a cutout inspired variant, SpecBlur (a novel approach). Augmentation parameters linearly increase in a curriculum based approach.
  • Aggregated Cross Entropy loss instead of CTC loss for easier training
  • Unsupervised Data Augmentation as means for Semi-Supervised Learning

Requirements

  • ariar2c
  • python3.x
  • libraries in requirements.txt

Download & Setup

Librispeech & CommonVoice datasets using download scripts, change dir parameter as per your configuration

sh download_scripts/download_librispeech.sh
sh download_scripts/extract_librispeech_tars.sh
sh download_scripts/download_common_voice.sh
sh download_scripts/extract_common_voice_tars.sh

Setup sentencepeiece vocab & form LMDB dataset.

sh dataset_scripts/librispeech_all_lines.sh
sh dataset_scripts/librispeech_sentencepiece_model.sh
OMP_NUM_THREADS="1" OPENBLAS_NUM_THREADS="1" python3 -W ignore -m dataset_scripts.create_librispeech_lmdb
OMP_NUM_THREADS="1" OPENBLAS_NUM_THREADS="1" python3 -W ignore -m dataset_scripts.create_commonvoice_lmdb
OMP_NUM_THREADS="1" OPENBLAS_NUM_THREADS="1" python3 -W ignore -m dataset_scripts.create_airtel_lmdb
OMP_NUM_THREADS="1" OPENBLAS_NUM_THREADS="1" python3 -W ignore -m dataset_scripts.create_airtelpayments_lmdb

Training

Modify utils/config.py as per your configuration and run

OMP_NUM_THREADS="1" CUDA_VISIBLE_DEVICES="0,1,2" python3.6 train.py

References

Papers

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

Jasper: An End-to-End Convolutional Neural Acoustic Model

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

Improved Regularization of Convolutional Neural Networks with Cutout

On the Variance of the Adaptive Learning Rate and Beyond

Aggregation Cross-Entropy for Sequence Recognition

MixMatch: A Holistic Approach to Semi-Supervised Learning

MixConv: Mixed Depthwise Convolutional Kernels

Unsupervised Data Augmentation for Consistency Training

Cyclical Learning Rates for Training Neural Networks

Cycle-consistency training for end-to-end speech recognition

RandAugment: Practical data augmentation with no separate search

Self-Attention Networks For Connectionist Temporal Classification in Speech Recognition

Codebases

DeepSpeech2

NVIDIA Neural Modules: NeMo

RAdam

LR-Finder

Cyclical Learning Rate Scheduler With Decay in Pytorch

MixNet

saber's People

Contributors

viig99 avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.