zw76859420 / ASR_Theory
语音识别理论、论文和PPT
☆604Updated 9 months ago
Alternatives and similar repositories for ASR_Theory:
Users that are interested in ASR_Theory are comparing it to the libraries listed below
- 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☆473Updated last month
- 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
- 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。☆670Updated last week
- 使用python进行语音识别☆155Updated 3 years ago
- 中文语音识别☆831Updated 6 years ago
- 基于卷积神经网络的语音识别声学模型的研究☆174Updated 5 years 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 No-Recurrence Sequence-to-Sequence Model for Speech Recognition☆375Updated 2 years ago
- 端到端中文语音识别☆88Updated 9 months ago
- ASR中文语音识别☆34Updated 5 years ago
- A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.☆788Updated 2 years ago
- 使用Tensorflow实现声纹识别☆310Updated 10 months ago
- 中文语音识别; Mandarin Automatic Speech Recognition;☆1,938Updated 9 months ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit