adiyoss / deepvot Goto Github PK

View Code? Open in Web Editor NEW

6.0 3.0 8.0 138.09 MB

Automatic Measurement of Voice Onset Time (VOT) using Deep Recurrent Neural Networks (Interspeech 2016)

License: MIT License

Python 44.03% Shell 0.60% Lua 55.37%

vot voice-onset-time recurrent-neural-networks phonetic-algorithm deep-learning machine-learning

deepvot's People

Contributors

Stargazers

Watchers

Forkers

mlspeech ebuz yosishrem pr-crypto idog-ceva jihwanparkpreprocessing gary109

deepvot's Issues

Too many paths to consider

Hi,

While I love the effort, there are many dependencies and library paths that need to be set up to get this to work.

On OSX Catallina (and after having installed according to the instructions) i get this:

$ python predict.py test_data/orig/bun.wav test_data/prediction/bun.TextGrid 0.0 0.2

1) Extracting features and classifying ...
12:17:37.946 [VotFrontEnd2] INFO: Processing 1 instances.
12:17:37.964 [VotFrontEnd2] INFO: Features extraction completed.

==> processing options	
==> load test file	

==> loading model	
/Users/frkkan96/torch/install/bin/luajit: /Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:343: unknown Torch class <nn.LinearNoBias>
stack traceback:
	[C]: in function 'error'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:343: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/nn/Module.lua:192: in function 'read'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:351: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/nn/Module.lua:192: in function 'read'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:351: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
	...
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:351: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/nn/Module.lua:192: in function 'read'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:351: in function 'readObject'
	/Users/frkkan96/torch/install/share/lua/5.1/torch/File.lua:409: in function 'load'
	classify_multi_class.lua:64: in main chunk
	[C]: in function 'dofile'
	...an96/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
	[C]: at 0x010c4e9b00

3) Extract Durations ...
Traceback (most recent call last):
  File "predict.py", line 57, in <module>
    predict(args.input_path, args.output_path, args.start_extract, args.end_extract)
  File "predict.py", line 38, in predict
    post_process(prob_file, predict_file)
  File "/Users/frkkan96/Documents/src/DeepVOT/run_all/post_process.py", line 12, in post_process
    with open(prob_file) as f:
IOError: [Errno 2] No such file or directory: '/Users/frkkan96/Documents/src/DeepVOT/run_all/tmp_files/tmp.prob'

It seems that torch cannot find the rnn library I installed. So, how do I make it find the library?

x86_64 builds of sbin/VotFrontEnd2 and sbin/VowelDurationFrontEnd?

Trying to run DeepVOT on Scientific Linux 7.6. macOS is unfortunately not an option.

All deps satisfied inc'l sox but the other Mach-O executables in run_all/sbin are a showstopper.

Any chance for x86_64 binaries, or a way to build from source?

"Bad CPU type in executable" and other issues

Hi,

I am kinda rookie.

I am running Mac OS10.15: Catalina.

I tried running the test example using

python predict.py test_data/orig/bun.wav test_data/prediction/bun.TextGrid 0.0 0.2

I get the following errors:

`1) Extracting features and classifying ...
/bin/sh: sbin/sox: Bad CPU type in executable
00:24:20.532 [VotFrontEnd2] INFO: Processing 1 instances.
Errror: Could not open file tmp/tmp.wav for reading.

==> processing options
==> load test file

==> ERROR: cannot read file.
/Users/XXXX/torch/install/bin/lua: utils.lua:47: attempt to index global 'dims' (a nil value)
stack traceback:
utils.lua:47: in function 'load_data'
classify_multi_class.lua:53: in main chunk
[C]: in function 'dofile'
...rs02/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: in ?

Extract Durations ...
Traceback (most recent call last):
File "predict.py", line 57, in
predict(args.input_path, args.output_path, args.start_extract, args.end_extract)
File "predict.py", line 38, in predict
post_process(prob_file, predict_file)
File "/Users/XXXX/DeepVOT/run_all/post_process.py", line 12, in post_process
with open(prob_file) as f:
IOError: [Errno 2] No such file or directory: '/Users/XXXX/DeepVOT/run_all/tmp_files/tmp.prob'`

Any pointer will be highly appreciated!

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.