dejavu
dejavu copied to clipboard
worldveil
Audio fingerprinting and recognition in Python
Hello! I tried to match podcasts using dejavu. Perhaps someone has already solved a similar problem and knows the best parameters for this, or is not suitable for content that...
Good afternoon worldveil, First, terrific package. Really easy to follow a fairly complex topic. I just finished upgrading the dejavu audio fingerprinting code to Python 3. Took a while to...
可否请解释一下这个公式： nseconds = round(float(offset) / DEFAULT_FS * DEFAULT_WINDOW_SIZE * DEFAULT_OVERLAP_RATIO, 5) 我的理解这句是想得到offset的物理偏移时间，我的理解是float(offset) / DEFAULT_FS 就就够了，因为offset其实是也是偏移了的点的个数。 [email protected]
I have added about 13 MP3s to the database, using the following script: ``` import json from dejavu import Dejavu from dejavu.logic.recognizer.file_recognizer import FileRecognizer from dejavu.logic.recognizer.microphone_recognizer import MicrophoneRecognizer # load...
 may the param match this
In ```__init__.py: Dejavu.align_matches(self, matches)``` is the following code: ``` nseconds = round(float(largest) / fingerprint.DEFAULT_FS * fingerprint.DEFAULT_WINDOW_SIZE * fingerprint.DEFAULT_OVERLAP_RATIO, 5) ``` This code does not take the sample rate into account....
Hi all, I tried to recognize a song, 'query_time' is very good ( 0.7199628353118896 s) After I tried to recognize 10 songs at the same time , 'query_time' took lots...
I change `hashes_matched` variable to fix a bug that I mentioned in #242 . This change make `dedup_hashes: Dict[str, int]` argument of the function (in line 175) not used, but...
Hi. I found a possible bug in `align_matches` function of Dejavu class. (dejavu/dejavu/__init__.py) In the line 208, the function assigns `dedup_hashes[song_id]` to `hashes_matched`. `dedup_hashes[song_id]` is a number of matched hashes...
Should I fingerprint 1000 songs per a period of time. Or fingerprint 40K only one time ?
