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。
☆487Updated last year
Related projects ⓘ
Alternatives and complementary repositories for FastASR
- 📣 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 …☆508Updated 6 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…☆405Updated 10 months ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆371Updated 5 months ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆463Updated 3 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☆461Updated last month
- 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☆249Updated last year
- 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。☆622Updated this week
- KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-…☆494Updated 10 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☆229Updated this week
- The dataset of Speech Recognition☆387Updated 4 months ago
- A 10000+ hours dataset for Chinese speech recognition☆506Updated last year
- Text Normalization & Inverse Text Normalization☆480Updated last week
- Speech-to-text server framework with next-gen Kaldi☆561Updated this week
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆445Updated 2 months ago
- 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 …☆465Updated 2 years ago
- Port of Funasr's Sense-voice model in C/C++☆163Updated 3 weeks ago
- chinese speech pretrained models☆1,035Updated 2 months ago
- 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☆817Updated this week
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆888Updated 4 months ago
- 中文标点符号模型，可以给文本添加标点符号。☆130Updated 8 months ago
- ☆82Updated last year
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆189Updated this week
- Chinese voice corpus. 中文语音语料，语音更加清晰自然，包含8个开源数据集，3200个说话人，900小时语音，1300万字。☆601Updated 4 years ago
- 超快的中文普通话TTS☆112Updated 3 years ago
- 端到端语音唤醒工具箱，从模型训练到模型推理。☆77Updated 2 months ago
- Chinese text normalization for speech processing☆627Updated last year
- Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, …☆1,065Updated 2 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。☆682Updated this week
- tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)☆525Updated last year
- ☆934Updated last week