garrywrj

bark

🔊 Text-Prompted Generative Audio Model

google-research

Google Research

transferlearning

Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

AudioGPT

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

cupy

NumPy & SciPy for GPU

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

awesome-speech-recognition-speech-synthesis-papers

Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)

nlp-competitions-list-review

复盘所有NLP比赛的TOP方案，只关注NLP比赛，持续更新中！

DeepFilterNet

Noise supression using deep filtering

NeuralSpeech

icefall

MQBench

Model Quantization Benchmark

ssast

Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".

onnx-tool

A parser, editor and profiler tool for ONNX models.

pyaec

simple and efficient python implemention of a series of adaptive filters. including time domain adaptive filters(lms、nlms、rls、ap、kalman)、nonlinear adaptive filters(volterra filter、functional link adaptive filters)、frequency domain adaptive filters(frequency domain adaptive filter、frequency domain kalman filter) for acoustic echo cancellation.

awesome-keyword-spotting

This repository is a curated list of awesome Speech Keyword Spotting (Wake-Up Word Detection).

EfficientWord-Net

OneShot Learning-based hotword detection.

malaya-speech

Speech Toolkit for Malaysian language, https://malaya-speech.readthedocs.io/

EfficientAT

This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.

FRA-RIR

3m-asr

3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition

ssspy

A Python toolkit for sound source separation.

Wav2Keyword

Wav2Keyword is keyword spotting(KWS) based on Wav2Vec 2.0. This model shows state-of-the-art in Speech commands dataset V1 and V2.

LLaMA-Pruning

Structural Pruning for LLaMA

unsup_speech_enh_adaptation

Unsupervised domain adaptation for conversational speech enhancement using RemixIT

Subband-Beamformer

webrtc_aec_using_kalmanAdaption

NeSsi

Keras/Pytorch neural network size, operations and parameters counter

fdlp_spectrogram

bssAuxFdica