EricFuma
My area of expertise involves multimodal text and speech, including Text-to-Speech, Voice Cloning, Voice Conversion, and Speech & Text LLM models.
AliPayHangZhou, China
Pinned Repositories
A_BASEMODEL_OF_INTENT-DETECTION
实现了一个意图检测的Baseline，并在 SMP2019 训练集上进行了简单的测试。模型还有许多地方需要调优，一些数据处理流程也不够规范，会在后续进行更新。
AI-Song-Cover-RVC
All in One Version : Youtube WAV Download, Separating Vocal, Splitting Audio, Training, and Inference Using Google Colab
Algorithm_github
依托Github项目，对典型题目做解答和剖析
ASR_TOOLS_WebUI
Bert-vits2转写和标注独立整合Webui,整合阿里FunAsr,必剪Asr以及Whisper大模型
audio-preprocess
Preprocess Audio for training
Basic_Module
用Numpy或Tensorflow矩阵操作实现卷积、self-attention、Seq2Seq-attention等基础模块的功能
CS-Notes
:books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计、Java、Python、C++
jianzhiOffer-Python-Coding
剑指OFFER第二版每一题的多解法思考（包括官方思路和Leetcode上一些巧妙的思路）
KAN-TTS
KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech
Pytorch_for_NLP
用pytorch处理中文/英文自然语言理解问题，记录如何一步步处理纯文本、使用深度学习模型解决问题，主要用于自己学习
EricFuma's Repositories
EricFuma/A_BASEMODEL_OF_INTENT-DETECTION
实现了一个意图检测的Baseline，并在 SMP2019 训练集上进行了简单的测试。模型还有许多地方需要调优，一些数据处理流程也不够规范，会在后续进行更新。
EricFuma/Pytorch_for_NLP
用pytorch处理中文/英文自然语言理解问题，记录如何一步步处理纯文本、使用深度学习模型解决问题，主要用于自己学习
EricFuma/KAN-TTS
KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech
EricFuma/jianzhiOffer-Python-Coding
剑指OFFER第二版每一题的多解法思考（包括官方思路和Leetcode上一些巧妙的思路）
EricFuma/AI-Song-Cover-RVC
All in One Version : Youtube WAV Download, Separating Vocal, Splitting Audio, Training, and Inference Using Google Colab
EricFuma/Algorithm_github
依托Github项目，对典型题目做解答和剖析
EricFuma/ASR_TOOLS_WebUI
Bert-vits2转写和标注独立整合Webui,整合阿里FunAsr,必剪Asr以及Whisper大模型
EricFuma/audio-preprocess
Preprocess Audio for training
EricFuma/Basic_Module
用Numpy或Tensorflow矩阵操作实现卷积、self-attention、Seq2Seq-attention等基础模块的功能
EricFuma/CS-Notes
:books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计、Java、Python、C++
EricFuma/espnet
End-to-End Speech Processing Toolkit
EricFuma/FunCodec
FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.
EricFuma/JA2ML-VITS
Japanese Dataset to Multi Language TTS （单一语种 --> 多语种 TTS，若训练出中文是否有大佐味）
EricFuma/megatts2
Unoffical implement of Megatts2
EricFuma/NLP-BaseModel
EricFuma/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
EricFuma/NLP_ability
总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力
EricFuma/SECap
EricFuma/Understanding-VITS
In this repository, you will learn how code works in VITS(Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech) in Jupyter Notebooks, including normalizing data, training process, inference process, and model's details.