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
☆460Updated last year
Related projects: ⓘ
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆436Updated last month
- A 10000+ hours dataset for Chinese speech recognition☆490Updated 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。☆590Updated last week
- The dataset of Speech Recognition☆382Updated 2 months ago
- Chinese text normalization for speech processing☆620Updated last year
- 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☆244Updated 3 years ago
- tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)☆516Updated last year
- 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。☆667Updated 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☆300Updated 2 years ago
- ☆419Updated this week
- 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…☆393Updated 4 years ago
- A No-Recurrence Sequence-to-Sequence Model for Speech Recognition☆372Updated 2 years ago
- 语音识别理论、论文和PPT☆579Updated last month
- 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…☆482Updated last year
- Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)☆121Updated last year
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆367Updated 3 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☆213Updated 2 weeks ago
- PAddle PARAllel text-to-speech toolKIT (supporting Tacotron2, Transformer TTS, FastSpeech2/FastPitch, SpeedySpeech, WaveFlow and Paralle…☆600Updated 2 years ago
- An Open Source Tools for Speaker Recognition☆590Updated last month
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆426Updated last week
- a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi☆338Updated 3 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☆174Updated 2 years ago
- A Demo of Mandarin/Chinese TTS frontend☆275Updated 2 years 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☆805Updated 2 months ago
- chinese speech pretrained models☆1,004Updated 3 weeks ago
- DaCiDian is an open-sourced chinese mandarin lexicon for automatic speech recognition(ASR)☆298Updated 4 years ago
- 端到端中文语音识别☆84Updated last month
- 使用Tensorflow实现声纹识别☆288Updated 3 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 …☆460Updated 2 years ago
- A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.☆768Updated last year