Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
DeepSpeech
Issue
D
DeepSpeech
项目概览
PaddlePaddle
/
DeepSpeech
9 个月 前同步成功
通知
200
Star
8425
Fork
1598
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
245
列表
看板
标记
里程碑
合并请求
3
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
D
DeepSpeech
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
245
Issue
245
列表
看板
标记
里程碑
合并请求
3
合并请求
3
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
开放中
245
已关闭
184
全部
429
新建issue
最近的搜索
{{formattedKey}}
{{ title }}
{{ help }}
{{name}}
@{{username}}
无
任何
{{name}}
@{{username}}
无
任何
{{name}}
@{{username}}
无
任何
{{name}}
@{{username}}
无
任何
即将开始
已启动
{{title}}
无
任何
{{title}}
无
任何
{{title}}
无
任何
{{name}}
是
否
是
否
{{title}}
{{title}}
手动
优先
创建日期
最近更新
里程碑截止日期
截止日期
人气
标记优先级
手动
Docker pull error
#477
· opened
7月 17, 2020
by
saxon_zh
0
更新于
7月 17, 2020
异步数据读取和处理效率不高,导致GPU利用率较低
#447
· opened
4月 28, 2020
by
saxon_zh
1
更新于
4月 29, 2020
支持实时的语音识别吗?
#478
· opened
7月 23, 2020
by
saxon_zh
0
更新于
7月 23, 2020
Segmentation Fault error for large wav files
#446
· opened
4月 21, 2020
by
saxon_zh
0
更新于
4月 21, 2020
感谢,在tiny目录下sh run_train.sh时报错
#442
· opened
4月 09, 2020
by
saxon_zh
1
更新于
4月 09, 2020
关于语音识别的实时聊天
#441
· opened
4月 06, 2020
by
saxon_zh
0
更新于
4月 06, 2020
Is Baidu Internal English Dataset clean voice?
#475
· opened
7月 13, 2020
by
saxon_zh
0
更新于
7月 13, 2020
同一份自己录制的语音,本人普通话不是很标准,但是科大讯飞的识别率几乎100%,百度这个的偏差也太大了。
#426
· opened
2月 20, 2020
by
saxon_zh
1
更新于
2月 24, 2020
Facing problem with installation on python3i
#421
· opened
1月 30, 2020
by
saxon_zh
6
更新于
5月 24, 2020
Error: You are not allowed to load partial data via load_combine_op, use load_op instead
#408
· opened
1月 03, 2020
by
saxon_zh
10
更新于
5月 20, 2020
Error to run inference and test scripts in chinese
#487
· opened
8月 13, 2020
by
saxon_zh
0
更新于
8月 13, 2020
examples/baidu_en8k/run_test_golden.sh 出錯
#457
· opened
5月 28, 2020
by
saxon_zh
1
更新于
8月 14, 2020
请问如何直接预测自己的录音,将录音转成文本
#452
· opened
5月 17, 2020
by
saxon_zh
4
更新于
5月 19, 2020
加载预训练模型后,报RuntimeError: Shape not matching
#450
· opened
5月 13, 2020
by
saxon_zh
3
更新于
5月 20, 2020
paddlepaddle 如何统计模型的参数量
#432
· opened
3月 10, 2020
by
saxon_zh
0
更新于
3月 10, 2020
请问大家都是怎么设置自己的参数的?遇到梯度爆炸大家都调整了什么呢?
#456
· opened
5月 28, 2020
by
saxon_zh
0
更新于
5月 28, 2020
docker image for cpu
#416
· opened
1月 21, 2020
by
saxon_zh
2
更新于
2月 24, 2020
Error: The fed Variable text_data should have dimensions = 2, shape = [-1, 1], but received fed shape [402]
#433
· opened
3月 18, 2020
by
saxon_zh
1
更新于
3月 23, 2020
按照readme 一步一步执行的, infer 时报错。
#404
· opened
12月 25, 2019
by
saxon_zh
3
更新于
1月 09, 2020
Speaker Diarilization
#485
· opened
8月 11, 2020
by
saxon_zh
0
更新于
8月 11, 2020
非常感谢
#25
· opened
11月 20, 2017
by
saxon_zh
7
更新于
11月 10, 2018
Upload the Docker image for users in China
#33
· opened
11月 28, 2017
by
saxon_zh
0
更新于
11月 29, 2017
Build Docker image for cloud training
#34
· opened
11月 28, 2017
by
saxon_zh
0
更新于
11月 29, 2017
BaiduCN1.2k Model 显示 to-be added?
#43
· opened
11月 30, 2017
by
saxon_zh
7
更新于
12月 28, 2017
Wers computed diff from kaldi
#45
· opened
12月 01, 2017
by
saxon_zh
7
更新于
12月 11, 2017
c/c++ decoder
#48
· opened
12月 04, 2017
by
saxon_zh
5
更新于
4月 20, 2018
switching language model at runtime
#49
· opened
12月 04, 2017
by
saxon_zh
1
更新于
12月 04, 2017
Data augmentor problem
#63
· opened
12月 06, 2017
by
saxon_zh
4
更新于
12月 07, 2017
/DeepSpeech/examples/tiny# sh run_train.sh 运行时出错
#64
· opened
12月 07, 2017
by
saxon_zh
4
更新于
3月 22, 2018
'superimpose' method in 'data_utils/audio.py'
#69
· opened
12月 09, 2017
by
saxon_zh
0
更新于
12月 09, 2017
'slice_from_file' in 'data_util/audio.py'
#70
· opened
12月 09, 2017
by
saxon_zh
1
更新于
12月 10, 2017
Problem about Librispeech data process and training params
#72
· opened
12月 11, 2017
by
saxon_zh
3
更新于
12月 19, 2017
中文语言模型无法下载,下了几十M之后就像断了,一直都这样
#74
· opened
12月 11, 2017
by
saxon_zh
6
更新于
12月 14, 2017
run_train.sh出错
#75
· opened
12月 12, 2017
by
saxon_zh
4
更新于
12月 12, 2017
decoder_utils.h:55: Error: Syntax error in input(1).
#76
· opened
12月 12, 2017
by
saxon_zh
3
更新于
3月 31, 2018
lanaguge model 的blank id能从0 开始吗?
#79
· opened
12月 14, 2017
by
saxon_zh
9
更新于
12月 14, 2017
run deploy/demo_client.py error
#81
· opened
12月 18, 2017
by
saxon_zh
2
更新于
12月 18, 2017
Abort while training
#82
· opened
12月 19, 2017
by
saxon_zh
6
更新于
12月 19, 2017
What language model do you use in the LibriSpeech benchmark?
#84
· opened
12月 19, 2017
by
saxon_zh
3
更新于
11月 28, 2018
batch-norm paramters
#85
· opened
12月 19, 2017
by
saxon_zh
6
更新于
1月 19, 2019
bidirectional_gru_bn_layer问题
#86
· opened
12月 19, 2017
by
saxon_zh
1
更新于
12月 19, 2017
The WER comparison between current benchmark and DS2 paper
#93
· opened
12月 21, 2017
by
saxon_zh
0
更新于
12月 21, 2017
BaiduCN1.2k Model识别结果不对
#94
· opened
12月 21, 2017
by
saxon_zh
11
更新于
1月 13, 2020
IOError: got end of file during message when training with CPU
#96
· opened
12月 22, 2017
by
saxon_zh
6
更新于
1月 31, 2018
demo_client.py IOError: [Errno -9996] Invalid input device (no default output device)
#98
· opened
12月 23, 2017
by
saxon_zh
1
更新于
12月 23, 2017
BaiduEN8k Model Configuration
#100
· opened
12月 28, 2017
by
saxon_zh
7
更新于
12月 30, 2017
Training details of the downloadable librispeech model
#106
· opened
1月 04, 2018
by
saxon_zh
0
更新于
1月 04, 2018
PaddlePaddle新年大礼!周边产品送不停!
#107
· opened
1月 04, 2018
by
saxon_zh
7
更新于
3月 01, 2018
无法安装,一直提示ImportError: No module named swig_decoders
#113
· opened
1月 09, 2018
by
saxon_zh
14
更新于
3月 06, 2020
Failed to train LibriSpeech using example script.
#114
· opened
1月 10, 2018
by
saxon_zh
5
更新于
1月 12, 2018
demo_server用cn 1.2k推荐什么配置?
#116
· opened
1月 11, 2018
by
saxon_zh
12
更新于
6月 19, 2019
Aishell testing data benchmark
#118
· opened
1月 12, 2018
by
saxon_zh
5
更新于
2月 12, 2018
Mandarin LM query speed is very slow
#119
· opened
1月 12, 2018
by
saxon_zh
3
更新于
2月 23, 2018
Aborted at 1515694750 (unix time) try "date -d @1515694750" if you are using GNU date
#123
· opened
1月 13, 2018
by
saxon_zh
5
更新于
3月 13, 2018
inference in real time
#124
· opened
1月 15, 2018
by
saxon_zh
9
更新于
2月 12, 2020
感谢,如果用DeepSpeech做孤立词识别,有没有比较好的建议,从数据准备到模型训练等
#126
· opened
1月 17, 2018
by
saxon_zh
3
更新于
9月 03, 2018
Context window width- feed forward question
#128
· opened
1月 18, 2018
by
saxon_zh
3
更新于
1月 18, 2018
log10(0) in rms_db(self)
#131
· opened
1月 22, 2018
by
saxon_zh
2
更新于
1月 22, 2018
incorporate hints in the decoding phase
#132
· opened
1月 23, 2018
by
saxon_zh
4
更新于
1月 26, 2018
maximum length of audio clip that can be transcribed using en8k model
#133
· opened
1月 23, 2018
by
saxon_zh
2
更新于
9月 16, 2018
changing the ctc_beam_search_decoder.cpp function
#135
· opened
1月 24, 2018
by
saxon_zh
2
更新于
1月 26, 2018
Floating point exception in ctc_beam_search_decoder
#136
· opened
1月 24, 2018
by
saxon_zh
2
更新于
5月 31, 2018
aishell cn model, different results between warm test and demo client
#137
· opened
1月 25, 2018
by
saxon_zh
2
更新于
1月 29, 2018
mac下运行run_train.sh运行报错
#139
· opened
1月 28, 2018
by
saxon_zh
6
更新于
8月 15, 2019
Floaing point exception in demo_server.py
#141
· opened
1月 29, 2018
by
saxon_zh
3
更新于
11月 06, 2019
Find a bug in data_utils/audio.py
#145
· opened
2月 01, 2018
by
saxon_zh
1
更新于
2月 01, 2018
can I enlarge the size of characters in the vocab.txt of the existing model?
#147
· opened
2月 02, 2018
by
saxon_zh
2
更新于
2月 03, 2018
improving location name (beijing, mumbai etc) recognition accuracy
#150
· opened
2月 03, 2018
by
saxon_zh
8
更新于
2月 10, 2018
Do I need to create my own Language Model if I generate a ASR model?
#151
· opened
2月 05, 2018
by
saxon_zh
2
更新于
2月 06, 2018
silence detection using cutoff on the acoustic probabilities
#156
· opened
2月 09, 2018
by
saxon_zh
1
更新于
2月 11, 2018
why low test WER on CHiME, training on librispeech Acoustic Model
#157
· opened
2月 13, 2018
by
saxon_zh
2
更新于
2月 13, 2018
Is it possible to train from features file (MFCC) not wave files
#158
· opened
2月 13, 2018
by
saxon_zh
1
更新于
2月 22, 2018
decoder giving partial transcripts
#160
· opened
2月 22, 2018
by
saxon_zh
4
更新于
12月 03, 2019
How to create my own language model
#161
· opened
2月 23, 2018
by
saxon_zh
11
更新于
7月 23, 2018
aishell预训练模型的结果糟糕
#162
· opened
2月 23, 2018
by
saxon_zh
2
更新于
2月 25, 2018
ctc_beam_search_decoder documentation
#163
· opened
2月 27, 2018
by
saxon_zh
1
更新于
3月 07, 2018
训练集与测试集的音频时长需要严格相似?
#166
· opened
2月 28, 2018
by
saxon_zh
6
更新于
2月 01, 2019
TrainCost vs ValidationCost
#167
· opened
3月 04, 2018
by
saxon_zh
3
更新于
3月 14, 2018
only finetune last fc layer and other layers fixed
#168
· opened
3月 06, 2018
by
saxon_zh
2
更新于
10月 25, 2018
memory leak ctc_beam_search_decoder
#169
· opened
3月 07, 2018
by
saxon_zh
4
更新于
6月 18, 2020
Ubuntu14.04 安装过程问题总结
#170
· opened
3月 12, 2018
by
saxon_zh
3
更新于
3月 14, 2018
a bug in ctc beam search decoder
#171
· opened
3月 12, 2018
by
saxon_zh
2
更新于
3月 16, 2018
DeepSpeech 里面 setup.sh 安装swig_decoders报错的问题
#175
· opened
3月 14, 2018
by
saxon_zh
7
更新于
8月 24, 2019
GPU execution requested, but not compiled with GPU support **F0315 14:52:42.020200 70689 hl_warpctc_wrap.cc:131] Check failed: CTC_STATUS_SUCCESS == dynload::compute_ctc_loss(batchInput, batchGrad, cpuLabels, cpuLabelLengths, cpuInputLengths, numClasse...
#177
· opened
3月 15, 2018
by
saxon_zh
3
更新于
3月 15, 2018
运行过程中 CUDA out of memmory?
#178
· opened
3月 15, 2018
by
saxon_zh
9
更新于
3月 16, 2018
write audio feature generator in c/c++
#180
· opened
3月 17, 2018
by
saxon_zh
3
更新于
4月 17, 2018
训练过程中 Connection reset by peer,“ managers.py", line 759, result = conn.recv() IOError: [Errno 104] Connection reset by peer
#181
· opened
3月 19, 2018
by
saxon_zh
5
更新于
6月 18, 2019
我用自己训练的中文语言模型做测试,提示如下:
#182
· opened
3月 19, 2018
by
saxon_zh
3
更新于
11月 09, 2018
关于中文训练数据集AiShell标注文本的疑问
#183
· opened
3月 20, 2018
by
saxon_zh
2
更新于
3月 20, 2018
getting the loss of a audio file with a certain transcription
#186
· opened
3月 21, 2018
by
saxon_zh
4
更新于
10月 14, 2019
Memory leak.
#187
· opened
3月 22, 2018
by
saxon_zh
3
更新于
3月 27, 2018
preprocessing steps before training the LM
#189
· opened
3月 22, 2018
by
saxon_zh
0
更新于
3月 22, 2018
Inference using English model returns gibberish
#190
· opened
3月 23, 2018
by
saxon_zh
1
更新于
10月 21, 2019
下载Mandarin LM Small模型后端出现错误
#191
· opened
3月 25, 2018
by
saxon_zh
6
更新于
11月 15, 2018
Production Level DeepSpeech
#192
· opened
3月 26, 2018
by
saxon_zh
1
更新于
4月 20, 2018
run_train.sh example failure
#194
· opened
3月 28, 2018
by
saxon_zh
4
更新于
4月 03, 2018
用自己的训练集训练报错
#196
· opened
3月 28, 2018
by
saxon_zh
3
更新于
3月 28, 2018
ValidationCost increases after each pass
#197
· opened
3月 28, 2018
by
saxon_zh
3
更新于
3月 30, 2018
Support FP16 calculation
#199
· opened
3月 29, 2018
by
saxon_zh
1
更新于
4月 20, 2018
中文声韵母建模
#202
· opened
4月 04, 2018
by
saxon_zh
3
更新于
5月 03, 2018
1
2
3