Executedone / 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
☆256Updated last year
Alternatives and similar repositories for Chinese-FastSpeech2:
Users that are interested in Chinese-FastSpeech2 are comparing it to the libraries listed below
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆378Updated 7 months ago
- KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-…☆499Updated last year
- 基于PyTorch的VITS-BigVGAN的tts中文模型，加入韵律预测模型。☆194Updated 2 years ago
- Unoffical implementation of Megatts2☆274Updated 10 months ago
- A 10000+ hours dataset for Chinese speech recognition☆515Updated last year
- vits chinese, tts chinese, tts mandarin 史上训练最简单，音质最好的语音合成系统☆212Updated 3 years ago
- TTS appalication based on modelscope KAN-TTS☆43Updated 9 months ago
- text to speech using autoregressive transformer and VITS☆234Updated 9 months ago
- unofficial vits2-TTS implementation in pytorch☆505Updated 10 months ago
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆384Updated last year
- ☆186Updated 4 months ago
- 本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型，同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法☆247Updated 2 months ago
- 端到端语音唤醒工具箱，从模型训练到模型推理。☆96Updated 4 months ago
- The dataset of Speech Recognition☆400Updated last month
- 超快的中文普通话TTS☆117Updated 3 years ago
- Text Normalization & Inverse Text Normalization☆516Updated 2 months ago
- 这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小…☆495Updated last year
- A fast Text-to-Speech (TTS) model. Work well for English, Mandarin/Chinese, Japanese, Korean, Russian and Tibetan (so far). 快速语音合成模型，适用…☆255Updated last year
- Chinese Mandarin Grapheme-to-Phoneme Converter. 中文轉注音或拼音 (INTERSPEECH 2022)☆298Updated 3 months ago
- ☆99Updated last year
- Pseudo Streaming SenseVoice with Hotwords☆171Updated last month
- Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!☆1,174Updated 11 months ago
- 一个快速制作语音数据集的可视化工具☆193Updated 10 months ago
- Forced Alignment-MFA☆37Updated 2 years ago
- Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform☆433Updated 2 years ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆57Updated 3 weeks ago
- 中文标点符号模型，可以给文本添加标点符号。☆134Updated last month
- Preprocess Audio for training☆296Updated 3 months ago
- 语音数据集制作标记工具☆132Updated 2 years ago
- 基于 g2pW 提升 pypinyin 的准确性☆82Updated last year