Z-yq / TensorflowASR
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
☆474Updated last month
Alternatives and similar repositories for TensorflowASR:
Users that are interested in TensorflowASR are comparing it to the libraries listed below
- A 10000+ hours dataset for Chinese speech recognition☆533Updated last year
- The dataset of Speech Recognition☆413Updated 4 months ago
- tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)☆535Updated last year
- Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)☆123Updated 2 years ago
- Chinese text normalization for speech processing☆662Updated 2 years 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。☆671Updated last week
- An Automatic Speech Recognition Frame ,一个中文语音识别的完整框架, 提供了多个模型☆246Updated 4 years ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆389Updated 11 months ago
- A No-Recurrence Sequence-to-Sequence Model for Speech Recognition☆375Updated 2 years ago
- speech-aligner,是一个从“人声语音”及其“语言文本”,产生音素级别时间对齐标注的工具。speech-aligner, is a tool that generate phoneme-level alignment between human speech an…☆401Updated 5 years ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆546Updated 2 months ago
- (已过时)中文语音合成,改自 https://github.com/Rayhane-mamah/Tacotron-2 和 https://github.com/begeekmyfriend/Tacotron-2☆298Updated 3 years ago
- DaCiDian is an open-sourced chinese mandarin lexicon for automatic speech recognition(ASR)☆302Updated 4 years ago
- A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.☆788Updated 2 years 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☆265Updated last week
- 语音识别理论、论文和PPT☆604Updated 9 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 …☆473Updated 2 years ago
- A Demo of Mandarin/Chinese TTS frontend☆278Updated 3 years ago
- An Open Source Tools for Speaker Recognition☆613Updated 9 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。☆729Updated 4 months ago
- a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi☆339Updated 4 years ago
- 端到端中文语音识别☆88Updated 9 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…☆515Updated 2 years ago
- 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☆177Updated 3 years ago
- A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset☆347Updated 3 years ago
- 使用Tensorflow实现声纹识别☆310Updated 10 months ago
- PAddle PARAllel text-to-speech toolKIT (supporting Tacotron2, Transformer TTS, FastSpeech2/FastPitch, SpeedySpeech, WaveFlow and Paralle…☆605Updated 3 years 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