chenkui164 / FastASR
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+小时)， 所以识别效果也很好，可以媲美许多商用的ASR软件。
☆493Updated last year
Alternatives and similar repositories for FastASR:
Users that are interested in FastASR are comparing it to the libraries listed below
- 📣 商用级开源语音自动识别程序库，开箱即用，全平台支持，中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide …☆521Updated 8 months ago
- SummerTTS 是一个基于C++的独立编译的中文和英文语音合成项目，可以本地运行不需要网络，而且没有额外的依赖，一键编译完成即可用于中文和英文的语音合成。SummerTTS is a standalone Chinese and English speech synt…☆428Updated last month
- KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-…☆500Updated last year
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆491Updated 5 months ago
- 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☆253Updated last year
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆378Updated 7 months ago
- 一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目，CPU上的实时率(RTF)小于0.1☆469Updated 3 months ago
- A 10000+ hours dataset for Chinese speech recognition☆512Updated last year
- Port of Funasr's Sense-voice model in C/C++☆220Updated last week
- 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 last month
- Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei …☆469Updated 2 years ago
- Text Normalization & Inverse Text Normalization☆512Updated 2 months ago
- Speech-to-text server framework with next-gen Kaldi☆587Updated this week
- 基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型☆832Updated last week
- chinese speech pretrained models☆1,058Updated 4 months ago
- Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。☆630Updated last week
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆463Updated last week
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆223Updated last month
- tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)☆532Updated last year
- The dataset of Speech Recognition☆399Updated 3 weeks ago
- Automatic Speech Recognition(ASR), Text-To-Speech(TTS) engine. 中英语音识别、多角色语音合成，支持多语言，准确率高☆484Updated last month
- 中文标点符号模型，可以给文本添加标点符号。☆132Updated 3 weeks ago
- 超快的中文普通话TTS☆117Updated 3 years ago
- ☆97Updated last year
- ☆598Updated 7 months ago
- Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!☆1,173Updated 11 months ago
- 基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。☆700Updated 3 weeks ago
- 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…☆257Updated last year
- A demo of zh/Chinese Text to Speech system run on CPU in real time. 中文实时语音合成系统Demo☆176Updated 2 years ago