Comments (7)
From the constants in the fingerprinting module, you can derive it yourself.
https://github.com/worldveil/dejavu/blob/master/dejavu/fingerprint.py#L14
In the case of the ones that are in the current master, it would be:
1 sec / 44100 * 4096 * 0.5 = 46.4399 ms per offset
from dejavu.
offset_seconds means the match begin time? anybody who can tell me how to get the match begin time??
from dejavu.
diff
is the offset from the beginning of the audio file in WINDOW_SIZE
chunks.
Here only 2 hashes matched in alignment, meaning whatever you were looking for likely wasn't in the file you had dejavu listen to.
You only get negative diffs with erroneous hash alignments - thus whenever the diff is negative, there was no match in your database for the song you fingerprinted.
This isn't a bug, this is just how the library operates.
from dejavu.
Thanks for the clarification.
I've run another test and I've go Diff is 14472 with 5 offset-aligned matches", Is there an exact number of the diff and offset that when you get guarantees there was a match?
from dejavu.
No, there is no exact number.
The diff is simply the time offset into the song in which the matched audio was found. The number of offset-aligned matches is a measure of confidence, the higher the better.
from dejavu.
I've googled for window_size and cannot find good material on it.
What are the units of measuring WINDOW_SIZE and how can I convert them to seconds so that I can know where the matches begin?
Also, kindly point me to good material on WINDOW_SIZE.
Thanks in advance
from dejavu.
Yes, offset_seconds
is the number of seconds before the recognized clip starts.
from dejavu.
Related Issues (20)
- Which field in the results indicates the best match with the original song HOT 3
- run_tests.py: error: the following arguments are required src HOT 4
- Trying to fingerprint about 200 000 files. After 15000 files INSERT operation is very slow. HOT 1
- Do maximum_filter with cupy instead of scipy
- Failed to solve HOT 1
- Comparing short audio files
- Python Docker image bloated
- A directory of potentially duplicate audio files?
- it works well with python3.6 ~
- Not working for recordings
- Some errors when I use python3.7
- multiple concurrency
- Fingerprinting Audio With Differing Sample Rates HOT 1
- Jscght
- figerprinting file HOT 1
- Any way to generate the result image of the plots? HOT 1
- Does this package supports Python 3 HOT 4
- does this project work well on recognizing human speak? HOT 5
- Problem running the sample project HOT 1
- erors using fingerprint_file HOT 1
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.
from dejavu.