nl
|
053c990339
|
更新dict.txt
|
2020-10-22 20:00:21 +08:00 |
nl
|
600debf36e
|
update readme
|
2020-10-21 22:34:19 +08:00 |
nl
|
d1d8540d64
|
Merge branch 'master' of github.com:nl8590687/ASRT_SpeechRecognition
|
2020-09-30 18:08:33 +08:00 |
nl
|
9639d08d61
|
update readme
|
2020-09-30 18:02:37 +08:00 |
nl8590687
|
b0ea8b214b
|
Merge pull request #211 from wkyo/master
录音小工具代码规范化与重命名speech-recorder.py -> speech_recorder.py
|
2020-08-29 20:29:44 +08:00 |
wkyo
|
b41d3dec03
|
rename speech recorder and update
|
2020-08-21 12:03:26 +08:00 |
nl
|
1998073679
|
解决预测一次后图没了的问题
|
2020-08-19 15:38:24 +08:00 |
nl
|
87a0ca090e
|
自动创建保存模型的子目录
|
2020-08-10 16:35:40 +08:00 |
nl
|
c1eb8862fa
|
更新数据集的国内镜像链接
|
2020-07-21 20:30:47 +08:00 |
nl
|
74d5e40dea
|
修复部分代码对tf2.0的兼容问题
|
2020-05-30 12:52:53 +08:00 |
nl
|
4dad3e73e1
|
update readme
|
2020-05-29 19:16:08 +08:00 |
nl
|
82d4ea272c
|
update readme
|
2020-05-21 21:02:32 +08:00 |
nl8590687
|
3ab613de8c
|
Merge pull request #189 from zhangxu999/master
add reset_default_graph.
|
2020-05-20 15:05:31 +08:00 |
张旭
|
14bd31212c
|
add reset_default_graph.
修改获取tensor值的代码,添加重置TF 运行图的代码,解决了 预测函数多次运行越来越慢的问题。
|
2020-05-20 14:46:08 +08:00 |
nl
|
b2ba6318cd
|
update readme
|
2020-05-11 17:56:54 +08:00 |
nl
|
20f9a9c0fb
|
update readme
|
2020-04-18 14:35:39 +08:00 |
nl8590687
|
4e4aad07ce
|
Merge pull request #176 from PhanatosZou/master
Compatible with TF2.0
|
2020-03-28 21:33:40 +08:00 |
PhanatosZou
|
7b9630ac05
|
compatible with TF2.0
|
2020-03-26 14:04:53 -07:00 |
nl
|
a6a8af3695
|
update readme
|
2020-01-17 17:57:35 +08:00 |
nl
|
502e64e2bf
|
添加不限制时间长度的代码
|
2019-11-15 21:11:13 +08:00 |
nl
|
83c6c9503a
|
添加提示:注意,Thchs30和ST-CMDS都必须下载,缺一不可
|
2019-10-20 18:13:03 +08:00 |
nl
|
4e2b22260b
|
适应性修改
|
2019-09-18 14:29:55 +08:00 |
nl
|
3031dbbff5
|
modify md docs
|
2019-09-01 19:43:10 +08:00 |
nl
|
9115d177ef
|
添加新数据集的下载链接
|
2019-08-14 12:06:44 +08:00 |
nl
|
7b5a0fd48d
|
修复bug
|
2019-07-31 13:42:12 +08:00 |
nl
|
028653e1e0
|
对第202行除8模8的代码添加相关注释信息
|
2019-07-31 10:26:59 +08:00 |
nl
|
e4d664ab59
|
更新数据集下载链接
|
2019-07-09 11:52:02 +08:00 |
nl8590687
|
68d1e809a2
|
Update FUNDING.yml
|
2019-05-25 21:02:13 +08:00 |
nl8590687
|
3c377d55c8
|
Create FUNDING.yml
|
2019-05-25 20:59:52 +08:00 |
nl8590687
|
a7a00d8bc1
|
Create donate.md
|
2019-05-25 20:56:17 +08:00 |
nl
|
b02ff7e83d
|
add new open source dataset aidatatang_200zh in readme
|
2019-04-13 17:18:54 +08:00 |
nl
|
418c82637e
|
add raise value error for getfrequencyfeature function
|
2019-04-04 12:38:14 +08:00 |
nl
|
ba91bf935d
|
纠正dict里面的错误
|
2019-04-02 16:33:51 +08:00 |
nl
|
6579229d7d
|
更新拼音参数和几条文件路径,声学模型文件跟之前版本不再兼容,需要重新训练
|
2019-03-29 14:28:01 +08:00 |
nl
|
07c9b3600b
|
恢复两个拼音
|
2019-03-29 14:20:52 +08:00 |
nl8590687
|
d89cf79c54
|
Merge pull request #94 from luanxxys/master
correct few errors. Thanks to @luanxxys
|
2019-03-29 14:15:51 +08:00 |
s luanxxy
|
b7168a48ee
|
correct few errors
|
2019-03-28 19:24:13 +08:00 |
nl
|
3ba8c63441
|
添加恐慌模式算法,通过解码失败时回退若干字,实现鲁棒性更高的连续文本拼音转汉字HMM统计语言模型
|
2019-03-22 16:44:24 +08:00 |
nl
|
ccc723f644
|
add GetFreqFeat4 and update readme
|
2019-03-18 14:28:54 +08:00 |
nl
|
4ef5fa32e2
|
更新贡献者名单
|
2019-03-16 13:22:59 +08:00 |
nl
|
a37ce68e2f
|
fix datapath bug
|
2019-03-16 12:57:54 +08:00 |
nl
|
a18b234682
|
纠正dict.txt新增内容格式
|
2019-02-26 17:32:27 +08:00 |
nl
|
4ae5184980
|
纠正dict错误
|
2019-02-25 12:56:17 +08:00 |
nl
|
2de93ad0a1
|
add pinyin 'fang5'
|
2019-02-12 20:45:13 +08:00 |
nl8590687
|
db864ad394
|
Merge pull request #78 from Elvenisboy/patch-1
add nan3 to dict.txt
|
2019-02-11 20:25:26 +08:00 |
Fuling
|
272c26ffa9
|
add nan3 to dict.txt
|
2019-02-11 19:35:01 +08:00 |
nl
|
34a4dd8f76
|
将直接指定路径的参数投入使用,提高dict字典列表文件路径在不同运行环境下的适应度
|
2019-01-26 23:14:18 +08:00 |
nl
|
334029be88
|
update readme
|
2019-01-25 22:48:54 +08:00 |
nl8590687
|
c17b5ef490
|
Merge pull request #75 from CXXT-Projects/add-hdf5-saving
Added methods for saving HDF5 model
|
2019-01-21 20:39:34 +08:00 |
Yizheng Huang
|
f50f7bc81a
|
Update SpeechModel251.py
|
2019-01-21 20:28:43 +08:00 |