Pinned Repositories
athena
an open-source implementation of sequence-to-sequence based speech processing engine
Chinese-FastSpeech2
基于标贝数据继续训练,同时对原本的FastSpeech2模型做了改进,引入了韵律表征以及韵律预测模块,使中文发音更生动且富有节奏
chinese_speech_pretrain
chinese speech pretrained models
Cognitive-Speech-TTS
Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.
conformer
Implementation of the convolutional module from the Conformer paper, for use in Transformers
ctc-segmentation
Segment an audio file and obtain utterance alignments. (Python package)
openfst-python
fix build for openfst-python for newer python version (support 3.8 3.9 3.10 3.11)
SRILM
Mirror of SRILM
wordmaker
auto generate chinese words in huge text.
sdli1995's Repositories
sdli1995/openfst-python
fix build for openfst-python for newer python version (support 3.8 3.9 3.10 3.11)
sdli1995/athena
an open-source implementation of sequence-to-sequence based speech processing engine
sdli1995/Chinese-FastSpeech2
基于标贝数据继续训练,同时对原本的FastSpeech2模型做了改进,引入了韵律表征以及韵律预测模块,使中文发音更生动且富有节奏
sdli1995/chinese_speech_pretrain
chinese speech pretrained models
sdli1995/Cognitive-Speech-TTS
Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.
sdli1995/conformer
Implementation of the convolutional module from the Conformer paper, for use in Transformers
sdli1995/ctc-segmentation
Segment an audio file and obtain utterance alignments. (Python package)
sdli1995/CTCWordBeamSearch
Connectionist Temporal Classification (CTC) decoder with dictionary and language model.
sdli1995/DL-Compiler-Navigation
MLC Road Map
sdli1995/GenshinData
Repository containing the game data for the game Genshin Impact.
sdli1995/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
sdli1995/SRILM
Mirror of SRILM
sdli1995/deep-learning-benchmark
Deep Learning Benchmark for comparing the performance of DL frameworks, GPUs, and single vs half precision
sdli1995/Grasscutter_Resources
Certain anime game Repacked Resource from Multiple Sources
sdli1995/Il2CppDumper-YuanShen
Modified version of Il2CppDumper allows you to dump methods of UserAssembly.dll of the game Genshin Impact
sdli1995/KuiperInfer
带你从零实现一个高性能的深度学习推理库,Implement a high-performance deep learning inference library step by step
sdli1995/langchain-ChatGLM
langchain-ChatGLM, local knowledge based ChatGLM with langchain | 基于本地知识的 ChatGLM 问答
sdli1995/LibrosaCpp
LibrosaCpp is a c++ implemention of librosa to compute short-time fourier transform coefficients,mel spectrogram or mfcc
sdli1995/open-gpu-kernel-modules
NVIDIA Linux open GPU with P2P support
sdli1995/pacconfig
sdli1995/rwkv-qualcomm
Inference rwkv5 with Qualcomm AI Engine Direct SDK
sdli1995/singledigitRecognizing
use LeNet5 to classify chinese number 0~9
sdli1995/so-vits-svc
SoftVC VITS Singing Voice Conversion
sdli1995/Speech-Backbones
This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.
sdli1995/SpeechAlgorithms
Speech Algorithms Collections
sdli1995/srilm-patch
Add some function to srilm toolkit
sdli1995/VitsServer
🌻 A VITS ONNX server designed for fast inference 🔥
sdli1995/warp-rnnt
CUDA-Warp RNN-Transducer
sdli1995/warp-transducer
A fast parallel implementation of RNN Transducer.
sdli1995/Wwise-Unpacker
Unpack game audio Wwise files (pck, bnk) with hashcode