All geek questions in one place

Speaker recognition - bad request error at microsoft oxford

I am using the python shell specified in the SDK section. I am trying to register a voice file for the created profile using the python API.

I managed to create a profile and successfully view all profiles. But when I try to record a voice file (.wav) with a simple hello world phrase with the created profile, I get the error message "ERROR: root: Error enrolling profile." , which in the trace reports ' Exception: profile registration error: invalid request . I used it by importing the module into my python file, as well as on the command line, as described in the Readme.

I don't know if this API will work or not. I don’t think there is any other API for my little experiment. There are no correct answers even in the SDK questions section.

PS: This is my first question. Forgive my styles and formats. The following is a stack trace:

ERROR:root:Error enrolling profile.
127.0.0.1 - - [17/May/2016 15:55:44] "POST /verify-voice HTTP/1.1" 500 -
INFO:werkzeug:127.0.0.1 - - [17/May/2016 15:55:44] "POST /verify-voice HTTP/1.1" 500 -
Traceback (most recent call last):
  File "/Library/Python/2.7/site-packages/Flask-0.10.1-py2.7.egg/flask/app.py", line 1836, in __call__
    return self.wsgi_app(environ, start_response)
  File "/Library/Python/2.7/site-packages/Flask-0.10.1-py2.7.egg/flask/app.py", line 1820, in wsgi_app
    response = self.make_response(self.handle_exception(e))
  File "/Library/Python/2.7/site-packages/Flask-0.10.1-py2.7.egg/flask/app.py", line 1403, in handle_exception
    reraise(exc_type, exc_value, tb)
  File "/Library/Python/2.7/site-packages/Flask-0.10.1-py2.7.egg/flask/app.py", line 1817, in wsgi_app
    response = self.full_dispatch_request()
  File "/Library/Python/2.7/site-packages/Flask-0.10.1-py2.7.egg/flask/app.py", line 1477, in full_dispatch_request
    rv = self.handle_user_exception(e)
  File "/Library/Python/2.7/site-packages/Flask-0.10.1-py2.7.egg/flask/app.py", line 1381, in handle_user_exception
    reraise(exc_type, exc_value, tb)
  File "/Library/Python/2.7/site-packages/Flask-0.10.1-py2.7.egg/flask/app.py", line 1475, in full_dispatch_request
    rv = self.dispatch_request()
  File "/Library/Python/2.7/site-packages/Flask-0.10.1-py2.7.egg/flask/app.py", line 1461, in dispatch_request
    return self.view_functions[rule.endpoint](**req.view_args)
  File "/Rajagopal/Development/GitRepos/pet-projects/barabara-server/wsgi/barbara/views/users.py", line 57, in voice_register
    enroll_profile(app.config['MICROSOFT_SPEAKER_RECOGNITION_KEY'], user.speaker_profile_id, _created_file_path)
  File "/Rajagopal/Development/GitRepos/pet-projects/barabara-server/wsgi/oxford/speaker_recognition/Identification/EnrollProfile.py", line 48, in enroll_profile
    enrollment_response = helper.enroll_profile(profile_id, file_path)
  File "/Rajagopal/Development/GitRepos/pet-projects/barabara-server/wsgi/oxford/speaker_recognition/Identification/IdentificationServiceHttpClientHelper.py", line 155, in enroll_profile
    raise Exception('Error enrolling profile: ' + res.reason)
Exception: Error enrolling profile: Bad Request
-1
source share
1 answer

The speaker identification code requires that the audio recording of the registration should be at least 20 seconds and no more than 5 minutes. The minimum amount of final speech required for registration, after removal of silence, is 60 seconds "per.

+1
source

Source: https://habr.com/ru/post/1657164/

More articles:


All Articles