Tags:
speech, multispeech
Owner:
laurent.pierron@inria.fr
Transvox processes a speech file in order to fake it: the transformed voice must be unrecognizable when compared with the original sound but understandable.
Please log in to perform a job with this app.
usage: transvox [-h] infile {v2,v3} ... Fake a vocal file in order to make the initial voice unrecognizable but understandable. positional arguments: infile wave file to transform optional arguments: -h, --help show this help message and exit algorithms: {v2,v3} v2 is direct, v3 is iterative, see parameters below v2 transvox infile v2 [-h] [vocal_tract] [excitation] [phase] v3 transvox infile v3 [-h] [reference] [lquality] [iquality] v2 arguments: vocal_tract expansion factor of vocal tract [50..150] excitation expansion factor of excitation [50..150], default random phase expansion factor of phase [80..120], default random v3 arguments: reference transformation reference in [0..99999], default random. lquality integer in [0..20], best is 20, default 10. iquality integer in [1..100], best is 100, default 10
In input :
In output :
17/09/2015 : Version 3.1, third version
16/09/2015 : Version 2, second version
03/08/2015 : Version 1.0, initial version
This app id is : 36
This curl command will create a job, and return your job url, and also the average execution time
files and/or dataset are optionnal, think to remove them if not wantedcurl -H 'Authorization: Token token=<your_private_token>' -X POST -F job[webapp_id]=36 -F job[param]="" -F job[queue]=standard -F files[0]=@test.txt -F files[1]=@test2.csv -F job[file_url]=<my_file_url> -F job[dataset]=<my_dataset_name> https://allgo.inria.fr/api/v1/jobs
Then, check your job to get the url files with :
curl -H 'Authorization: Token token=<your_private_token>' -X GET https://allgo.inria.fr/api/v1/jobs/<job_id>