This is your work, valued

Peking

Fangjun Kuang

Elite
@csukuangfj

Was vorbei ist, ist vorbei.

kaldifeat. Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API

215

onnxruntime-libs. onnxruntime pre-compiled libs

197

kaldi-native-fbank. Kaldi-compatible online fbank extractor without external dependencies

152

code-for-Lucas-Kanade-20-Years-On. C

74

optimized_transducer. Memory efficient transducer loss computation

70

transducer-loss-benchmarking. Python

67

OpenCNN. An Open Convolutional Neural Network Framework in C++ From Scratch

67

PortAudioSharp2. C# binding for portaudio supporting Linux, macOS, Windows, iOS

51

kaldilm. Python wrapper for kaldi's arpa2fst

38

onnxruntime-build. A build project for ONNX Runtime

30

kaldi-hmm-gmm. C++

28

sherpa-onnx. C++

28

kaldi_native_io. python wrapper for kaldi's native I/O

27

ppm. PatchMatch algorithms for motion estimation and stereo reconstruction

17

naudiodon2. Node.js stream bindings for PortAudio

11

icefall. Python

11

vits_chinese. vits chinese, tts chinese, tts mandarin 史上训练最简单,音质最好的语音合成系统

9

Operating-Systems-Three-Easy-Pieces-all-in-one-pdf. Operating Systems: Three Easy Pieces All in One pdf

8

blas-lapack-in-c-cplusplus. Examples of using BLAS and Lapack in C and C++

7

portaudio-go. Go bindings for the PortAudio audio I/O library

7

vits-cantonese. VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai

6

sr-data. Speaker identification test data for sherpa-onnx

5

k2_decoding_benchmark. Python

4

ncnn. ncnn is a high-performance neural network inference framework optimized for the mobile platform

4

sherpa. Speech-to-text server framework with next-gen Kaldi

4

kfj-vim. My vim settings.

3

sherpa-ncnn. C++

2

tts-dataset-creation. Create dataset for tts

2

icefall-asr-conformer-ctc-bpe-500.

2

Matcha-TTS. [ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

1

csukuangfj.

1

memory-leak-example. CMake

1

subllm. This repository is the official implementation of the ECAI 2024 conference paper SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM

1

mecat. Python

1

cppjieba. "结巴"中文分词的C++版本

1

piper. A fast, local neural text to speech system

1

MeloTTS. High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

1