ishine Goto Github PK

alibi

PyTorch implementation of Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

aligntts

Implementation of ALIGNTTS: EFFICIENT FEED-FORWARD TEXT-TO-SPEECH SYSTEMWITHOUT EXPLICIT ALIGNMENT (arXiv:2003.01950v1 [eess.AS] 4 Mar 2020)

alimeeting

The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to provide participants with baseline systems for speech recognition and speaker diarization in conference scenario.

alta

An Automatic Lyrics Transcription Framework using Dilated Convolutional Neural Networks with Self-Attention based on kaldi

am-sincnet

amazonqa

Evidence-based QA system for community question answering.

amtl-bnfs-i-vector-based-lr

This is the implementation of an unpublished paper: Adversarial Multi-task deep feature and unsupervised back-end adpatation for language recognition

amusingpythoncodes

Interesting python codes to tackle simple machine/deep learning tasks

animateportrait

Code for "Animating Portrait Line Drawings from a Single Face Photo and a Speech Signal"

animeganv2

[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

animeganv3

Use AnimeGANv3 to make your own animation works, including turning photos or videos into anime.

annotated-s4

Implementation of https://srush.github.io/annotated-s4

anofed

用于标注、查看和修改结果的中文NLP分词工具

answer

基于本体的语义搜索引擎-Answer-V0.9　问答系统

apb2facev2

An improved version of APB2Face: Real-Time Audio-Guided Multi-Face Reenactment

apnet

approximate-memory-tests

aps

A workspace for single/multi-channel speech recognition & enhancement & separation.

arca23k-dataset

The code used to create the ARCA23K and ARCA23K-FSD datasets

arm-neon-intrinsics

arm neon 相关文档和指令意义

array_synthesis

synthesis of basic array processing algorithms

arrayfire

ArrayFire: a general purpose GPU library.

asc_baseline

ash-ir-dataset

An impulse response dataset for binaural synthesis of spatial audio systems on headphones

asr

asr-decoder

it's ASR decoder and make graph project

asr-hybrid-decoding

This is an extension of kaldi speech recognition software which allows to perform decoding of speech with hybrid word and phoneme graphs. The output is a mix of in-vocabulary words and phoneme sequences. This decoding is suitable for systems with only a small dictionary available and for further recovery of OOV words.

asr-hybrid-decoding-1

asr-rescoring

asr-score

simple, dependency-free Word Error Rate calculator in python3