xinkez

alexa-end-to-end-slu

This setup allows to train end-to-end neural models for spoken language understanding (SLU).

apam

APAM toolkit is built on PyTorch and provides recipes to adapt pretrained acoustic models with a variety of sequence discriminative training criterions.

audio_source_separation

An implementation of audio source separation tools.

charsiu

Charsiu: A neural phonetic aligner.

CharsiuG2P

Multilingual G2P in over 100 languages

EfficientConformer

Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition

FastSpeech2

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

GigaSpeech

Large, modern dataset for speech recognition

GMM_VAD

kaldi-serve

Server framework for Kaldi ASR Toolkit

Lattice-ELMo

Source code for ACL 2020 paper "Learning Spoken Language Representations with Neural Lattice Language Modeling"

norbert

Painless Wiener filters for audio separation

OMLSA-IMCRA

Python implementation of OMLSA+IMCRA algorithm for speech enhancement.

OpenTransformer

A No-Recurrence Sequence-to-Sequence Model for Speech Recognition

PercepNet

(Under construct) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

pika

a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi

pygsound

Impulse response generation based on state-of-the-art geometric sound propagation engine.

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity and Number Detector

simpletransformers

Transformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

storir

supervoice-gpt

GPT-style network for phonemization with durations of text

torch-audiomentations

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

torchaudacity

PyTorch wrappers for using your model in audacity!

torchprof

PyTorch layer-by-layer model profiler

torchsubband

Pytorch implementation of subband decomposition

Transformer-Transducer

A pytorch implementation of Transformer Transducer(T-T)

VALL-E-X

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io

voice-activity-detection-2

Pytorch implementation of SELF-ATTENTIVE VAD, ICASSP 2021

voicefixer_main

General Speech Restoration

wikipron

Massively multilingual pronunciation mining