A pure PyTorch batched computation implementation of "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition"

Overview

torch-cif

A pure PyTorch batched computation implementation of "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/abs/1905.11235.

Usage

def cif_function(
    input: Tensor,
    alpha: Tensor,
    beta: float = 1.0,
    padding_mask: Optional[Tensor] = None,
    target_lengths: Optional[Tensor] = None,
    max_output_length: Optional[int] = None,
    eps: float = 1e-4,
) -> Tuple[Tensor, Tensor, Tensor]:
    r""" A batched computation implementation of continuous integrate and fire (CIF)
    https://arxiv.org/abs/1905.11235

    Args:
        input (Tensor): (N, S, C) Input features to be integrated.
        alpha (Tensor): (N, S) Weights corresponding to each elements in the
            input. It is expected to be after sigmoid function.
        beta (float): the threshold used for determine firing.
        padding_mask (Tensor, optional): (N, S) A binary mask representing
            padded elements in the input.
        target_lengths (Tensor, optional): (N,) Desired length of the targets
            for each sample in the minibatch.
        max_output_length (int, optional): The maximum valid output length used
            in inference. The alpha is scaled down if the sum exceeds this value.
        eps (float, optional): Epsilon to prevent underflow for divisions.
            Default: 1e-4

    Returns: Tuple (output, feat_lengths, alpha_sum)
        output (Tensor): (N, T, C) The output integrated from the source.
        feat_lengths (Tensor): (N,) The output length for each element in batch.
        alpha_sum (Tensor): (N,) The sum of alpha for each element in batch.
            Can be used to compute the quantity loss.
    """

Note

ℹ️ This is a WIP project. the implementation is still being tested.

  • This implementation uses cumsum and floor to determine the firing positions, and use scatter to merge the weighted source features.
  • Run test by python test.py (requires pip install expecttest).
  • Feel free to contact me if there are bugs in the code.

Reference

Owner
張致強
張致強
A Dataset for Direct Quotation Extraction and Attribution in News Articles.

DirectQuote - A Dataset for Direct Quotation Extraction and Attribution in News Articles DirectQuote is a corpus containing 19,760 paragraphs and 10,3

THUNLP-MT 9 Sep 23, 2022
ICS 4u HD project, start before-wards. A curtain shooting game using python.

Touhou-Star-Salvation HDCH ICS 4u HD project, start before-wards. A curtain shooting game using python and pygame. By Jason Li For arts and gameplay,

15 Dec 22, 2022
Predicting Auction Sale Price using the kaggle bulldozer auction sales data: Modeling with Ensembles vs Neural Network

Predicting Auction Sale Price using the kaggle bulldozer auction sales data: Modeling with Ensembles vs Neural Network The performances of tree ensemb

Mustapha Unubi Momoh 2 Sep 13, 2022
BARTScore: Evaluating Generated Text as Text Generation

This is the Repo for the paper: BARTScore: Evaluating Generated Text as Text Generation Updates 2021.06.28 Release online evaluation Demo 2021.06.25 R

NeuLab 196 Dec 17, 2022
HuSpaCy: industrial-strength Hungarian natural language processing

HuSpaCy: Industrial-strength Hungarian NLP HuSpaCy is a spaCy model and a library providing industrial-strength Hungarian language processing faciliti

HuSpaCy 120 Dec 14, 2022
Official code for the ICLR 2021 paper Neural ODE Processes

Neural ODE Processes Official code for the paper Neural ODE Processes (ICLR 2021). Abstract Neural Ordinary Differential Equations (NODEs) use a neura

Cristian Bodnar 50 Oct 28, 2022
Official and maintained implementation of the paper "OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data" [BMVC 2021].

OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data Christoph Reich, Tim Prangemeier, Özdemir Cetin & Heinz Koeppl | Pr

Christoph Reich 23 Sep 21, 2022
This repository contains the map content ontology used in narrative cartography

Narrative-cartography-ontology This repository contains the map content ontology used in narrative cartography, which is associated with a submission

Weiming Huang 0 Oct 31, 2021
🎯 A comprehensive gradient-free optimization framework written in Python

Solid is a Python framework for gradient-free optimization. It contains basic versions of many of the most common optimization algorithms that do not

Devin Soni 565 Dec 26, 2022
GNN-based Recommendation Benchma

GRecX A Fair Benchmark for GNN-based Recommendation Preliminary Comparison DiffNet-Yelp dataset (featureless) Algo 73 Oct 17, 2022

A PyTorch toolkit for 2D Human Pose Estimation.

PyTorch-Pose PyTorch-Pose is a PyTorch implementation of the general pipeline for 2D single human pose estimation. The aim is to provide the interface

Wei Yang 1.1k Dec 30, 2022
A GUI for Face Recognition, based upon Docker, Tkinter, GPU and a camera device.

Face Recognition GUI This repository is a GUI version of Face Recognition by Adam Geitgey, where e.g. Docker and Tkinter are utilized. All the materia

Kasper Henriksen 6 Dec 05, 2022
A PyTorch Implementation of the Luna: Linear Unified Nested Attention

Unofficial PyTorch implementation of Luna: Linear Unified Nested Attention The quadratic computational and memory complexities of the Transformer’s at

Soohwan Kim 32 Nov 07, 2022
PyTorch implementation of paper: AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer, ICCV 2021.

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer [Paper] [PyTorch Implementation] [Paddle Implementation] Overview This reposit

148 Dec 30, 2022
TigerLily: Finding drug interactions in silico with the Graph.

Drug Interaction Prediction with Tigerlily Documentation | Example Notebook | Youtube Video | Project Report Tigerlily is a TigerGraph based system de

Benedek Rozemberczki 91 Dec 30, 2022
这个开源项目主要是对经典的时间序列预测算法论文进行复现,模型主要参考自GluonTS,框架主要参考自Informer

Time Series Research with Torch 这个开源项目主要是对经典的时间序列预测算法论文进行复现,模型主要参考自GluonTS,框架主要参考自Informer。 建立原因 相较于mxnet和TF,Torch框架中的神经网络层需要提前指定输入维度: # 建立线性层 TensorF

Chi Zhang 85 Dec 29, 2022
Dynamic Head: Unifying Object Detection Heads with Attentions

Dynamic Head: Unifying Object Detection Heads with Attentions dyhead_video.mp4 This is the official implementation of CVPR 2021 paper "Dynamic Head: U

Microsoft 550 Dec 21, 2022
Flappy bird automation using Neuroevolution of Augmenting Topologies (NEAT) in Python

FlappyAI Flappy bird automation using Neuroevolution of Augmenting Topologies (NEAT) in Python Everything Used Genetic Algorithm especially NEAT conce

Eryawan Presma Y. 2 Mar 24, 2022
PyTorch implementation of normalizing flow models

PyTorch implementation of normalizing flow models

Vincent Stimper 242 Jan 02, 2023