pelhans / zasr_tensorflow Goto Github PK
View Code? Open in Web Editor NEWMandarin ASR system based on tensorflow
License: Apache License 2.0
Mandarin ASR system based on tensorflow
License: Apache License 2.0
Creating manifest data/aishell/manifest ...
Traceback (most recent call last):
File "data_utils/build_vocab.py", line 19, in
from utils.utility import add_arguments, print_arguments
ImportError: No module named utility
Build vocabulary failed. Terminated.
貌似这个utils.utility找不到。
我尝试重新安装了utils和utility都没有效果,请问改怎么处理啊
有没有现成的声学模型可以直接调用的?
tensorflow必须GPU调用的吗,你参考的那个git代码,貌似就是只能GPU
root@LAPTOP-LMKN11R5:/mnt/d/zasr/ZASR_tensorflow/example/aishell# ./run_data.sh
adsadas 6c58fe97d6afd67202da241e8c28c57d
Downloading http://www.openslr.org/resources/33/data_aishell.tgz ...
Will not apply HSTS. The HSTS database must be a regular and non-world-writable file.
ERROR: could not open HSTS store at '/root/.wget-hsts'. HSTS will be disabled.
--2018-08-09 16:11:37-- http://www.openslr.org/resources/33/data_aishell.tgz
Resolving www.openslr.org (www.openslr.org)... 46.101.158.64
Connecting to www.openslr.org (www.openslr.org)|46.101.158.64|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 15582913665 (15G) [application/x-gzip]
Saving to: ‘/media/nlp/23ACE59C56A55BF3/wav_file/aishell/data_aishell.tgz’
data_aishell.tgz 100%[===================>] 14.51G 8.04MB/s in 34m 25s
2018-08-09 16:46:02 (7.20 MB/s) - ‘/media/nlp/23ACE59C56A55BF3/wav_file/aishell/data_aishell.tgz’ saved [15582913665/15582913665]
MD5 Chesksum /media/nlp/23ACE59C56A55BF3/wav_file/aishell/data_aishell.tgz ...
Traceback (most recent call last):
File "data/aishell/aishell.py", line 119, in <module>
main()
File "data/aishell/aishell.py", line 115, in main
manifest_path=args.manifest_prefix)
File "data/aishell/aishell.py", line 94, in prepare_dataset
filepath = download(url, md5sum, target_dir)
File "/mnt/d/zasr/ZASR_tensorflow/data_utils/utility.py", line 76, in download
raise RuntimeError("MD5 checksum failed.")
Is it possible that the downloaded file is really broken or the MD5 checksum itself is wrong? Thanks in advance.
请问下训练需要多长时间,准确率如何,可以分享训练好的模型出来吗,谢谢
请问,目前的RNN-CTC是可以实现端到端的语音识别的,可以直接输出汉字,那这个模型里面有语言模型吗?如果没有是不是外加一个语言模型效果会不会有提升?如果可以,那么需要怎么外加语言模型?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.