iwaterxt

iwaterxt's Stars

• HqWu-HITCS/Awesome-Chinese-LLM

  整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

  17.3k219271.6k

• SYSTRAN/faster-whisper

  Faster Whisper transcription with CTranslate2

  Language:Python13.3k1257781.1k

• kyutai-labs/moshi

  Language:Python7.1k8096552

• InsaneLife/ChineseNLPCorpus

  中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

  Language:Python4.3k879789

• VITA-MLLM/VITA

  ✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM

  Language:Python1.1k386768

• NVIDIA/BigVGAN

  Official PyTorch implementation of BigVGAN (ICLR 2023)

  Language:Python930710111

• openspeech-team/openspeech

  Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

  Language:Python68418177115

• LinkSoul-AI/LLaSM

  第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。

  Language:Python54114955

• p0p4k/vits2_pytorch

  unofficial vits2-TTS implementation in pytorch

  Language:Python502255895

• DavidDiazGuerra/gpuRIR

  Python library for Room Impulse Response (RIR) simulation with GPU acceleration

  Language:Cuda500105996

• AkojimaSLP/Beamforming-for-speech-enhancement

  simple delaysum, MVDR and CGMM-MVDR

  Language:Python2466574

• Enny1991/beamformers

  Easy to use Beamformers for multi-channel speech separation/enhancement

  Language:Python1914449

• tencent-ailab/FRA-RIR

  Language:Python1808827

• anton-jeran/FAST-RIR

  This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.

  Language:Python1565428

• hlt-mt/mosel

  Collection of Open Source Speech Data

  151706

• robin1001/beamforming

  Language:C1418578

• LXP-Never/AEC_DeepModel

  基于深度学习的声学回声消除基线代码

  Language:Python1323539

• dengjunquan/DoA-Estimation-MUSIC-ESPRIT

  Direction of Arrival Estimation using MUSIC and ESPRIT Algorithms in Python

  Language:Python1233328

• LCAV/FRIDA

  A high-resolution direction-of-arrival finding algorithm relying on finite rate of innovation sampling with a robust reconstruction algorithm.

  Language:Python9314747

• nvidia-riva/riva-asrlib-decoder

  Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva

  Language:Python8372423

• jorgehatccrma/pyagc

  Python implementation for audio time-frequency automatic gain control

  Language:Python792122

• vell001/audio-annotator

  音频标注工具

  Language:JavaScript744031

• vkothapally/JAECBF

  Language:Python511110

• echocatzh/PFDKF

  partitioned block based frequency domain Kalman filter

  Language:Python39118

• iranroman/SpatialScaper

  Language:Jupyter Notebook302374

• ThomasHaubner/e2e_dnn_ad_control_for_lin_aec

  End-To-End Deep Learning-based Adaptation Control for Linear Acoustic Echo Cancellation

  Language:Python274212

• rrbluke/CNBF

  Complex Neural Beamformer

  Language:Python252012

• samuel-clarke/RealImpact

  Language:Jupyter Notebook22225

• rrbluke/BSSD

  Blind Source Separation and Dereverberation

  Language:Python19206

• abde92/Direction-of-Arrival-Estimation-for-RADAR

  In this repository, w implement a direction of arrivals (DoA) classic and super-resolution algorithms such Multi-signals Classification (MUSIC) and estimation of signal parameters via rotational invariant techniques (ESPRIT)

  Language:Python14407