包括 AISHELL-1_sample数据集 和词典

MASR中文语音识别模型 aishell (179小时)

AISHELL-3 is a large-scale and high-fidelity multi-speaker Mandarin speech corpus published by Beijing Shell Shell Technology Co.,Ltd. It can be used to train multi-speaker Text-to-Speech (TTS) systems.The corpus contains roughly 85 hours of emotion-neutral recordings spoken by 218 native Chinese mandarin speakers and total 88035 utterances. Their auxiliary attributes such as gender, age group and native accents are explicitly marked and provided in the corpus. Accordingly, transcripts in Chines

最全面的中英文语音数据集介绍（附加下载链接），包括LibriSpeech ASR corpus，TED-LIUM，THCHS-30，Aishell等

Pytorch实现的流式与非流式语音识别模型（数据集：AIShell），源码地址为：https://github.com/yeyupiaoling/MASR

PPASR中文语音识别（进阶级）模型（aishell数据集训练的），源码地址：https://github.com/yeyupiaoling/PPASR/tree/%E8%BF%9B%E9%98%B6%E7%BA%A7

PPASR中文语音识别（最终级）模型（aishell数据集训练的），源码地址：https://github.com/yeyupiaoling/PPASR

PaddlePaddle实现的DeepSpeech2模型，训练aishell数据集训练的模型，源码地址：https://github.com/yeyupiaoling/PaddlePaddle-DeepSpeech

包含mono、tri1、tri2、tri3a、tri4a、tri5a已训练好的mdl、fst等文件，不包含dnn训练结果

transformer应用到语音识别的一个项目源代码暂时还没开始复现