Functions — github.com/NaveedShahid/Voice-Authentication-CNN

CodeHub MCPcopy Create free account

hub / github.com/NaveedShahid/Voice-Authentication-CNN / functions

Functions14 in github.com/NaveedShahid/Voice-Authentication-CNN

⨍ Functions 14 ◇ Types & classes 0

↓ 3 callersFunctionget_embedding

(model, wav_file, max_time)

feature_extraction.py:31

↓ 2 callersFunctionbuckets

(max_time, steptime, frameskip)

feature_extraction.py:10

↓ 2 callersFunctionget_extension

voice_auth.py:138

↓ 2 callersFunctionget_fft_spectrum

(filename, buckets)

preprocess.py:36

↓ 1 callersFunctionargs

voice_auth.py:25

↓ 1 callersFunctionenroll

Enroll a user with an audio file inputs: str (Name of the person to be enrolled and registered) str (Path to the audio file of

voice_auth.py:42

↓ 1 callersFunctionenroll_csv

Enroll a list of users using csv file inputs: str (Path to comma seperated file for the path to voice & person to enroll) outputs: No

voice_auth.py:68

↓ 1 callersFunctionfile_choices

(choices,filename)

voice_auth.py:132

↓ 1 callersFunctionget_embeddings_from_list_file

(model, list_file, max_time)

feature_extraction.py:42

↓ 1 callersFunctionload

(filename, sample_rate)

preprocess.py:9

↓ 1 callersFunctionnormalize_frames

(m,epsilon=1e-12)

preprocess.py:15

↓ 1 callersFunctionrecognize

Recognize the input audio file by comparing to saved users' voice prints inputs: str (Path to audio file of unknown person to recognize)

voice_auth.py:96

↓ 1 callersFunctionremove_dc_and_dither

(sin, sample_rate)

preprocess.py:21

Functionget_embedding_batch

(model, wav_files, max_time)

feature_extraction.py:38