pfann
pfann copied to clipboard
stdio2016
Neural Network Audio FingerPrint
Hi, Looks like a really interesting project. Is it possible to add the MIT License file same as the original implementation? https://github.com/mimbres/neural-audio-fp/blob/main/LICENSE Many thanks, Harry
Hi there, 1st of all thanks for this awesome work ! Since we've 'doxed' it in our [HyMPS project](https://forart.it/HyMPS) (under [AUDIO section](https://github.com/forart/HyMPS#- ) \ [AIbased page](https://github.com/forart/HyMPS/blob/main/Audio/AI-based.md#-- ) \ [Fingerprinting](https://github.com/forart/HyMPS/blob/main/Audio/AI-based.md#fingerprinting-)), can...
Hello, I find your code very interesting. Instead of matching among multiple audio files, I am looking to modify the code to match a fragment of audio (3-10 seconds) within...
Is the loss function different from the original paper? Also the method to calculate validate score? I can't find any details about them in your thesis.
As line120 in `train.py`: ``` for x in tqdm(train_data, desc='train data', ncols=80): ``` Why do you use train data here?
python tools/audioset2.py lists/audioset1.csv ../pfann_dataset/audioset python tools/audioset2.py lists/audioset2.csv ../pfann_dataset/audioset python tools/audioset2.py lists/audioset3.csv ../pfann_dataset/audioset download -4N3GjgnIQ0 from 260 to 270 failed to download ;-( stop for a moment~~~ download -5lI0Wt-pNE from 250...
Expected format for /path/to/query6s/list.txt the input of the **matcher.py** is not explicit nor visible anywhere. Thanks for all your efforts, the library is great and inspiring
Currently my thesis is in Traditional Chinese. I want more people to see this research, so I am going to translate my thesis to English.
Hello, I know this might be too late to ask but can you provide some of your pretrained fp models? I saw that you have done experiments with many values...
