-
## ❓ Questions
Hello, my question is about reconstruction loss in frequency domain, in a paragraph 3.4 it is stated that you use "mel-spectrogram using a normalized STFT", what type of normalizatio…
-
Instead of having only two files as we are now (`functional.py` and `layers.py`), I'd like something like [I did on Kapre](https://github.com/keunwoochoi/kapre/tree/master/kapre) but slightly differen…
-
I had an error on this line
train_x, test_x, train_y, test_y = train_test_split(features, labels, test_size=0.3, random_state=0)
they said
ValueError: With n_samples=0, test_size=0.3 and trai…
-
Hi! I'm just following the tutorial doing these:
```
import openl3
model = openl3.models.load_audio_embedding_model(
input_repr="mel128",
content_type='music',
embedding_size=512,
)…
-
(Related to #64)
## Description
Before committing to an Object-Oriented interface of class + compute method, try out the approach outlined on #64 for only one or two algorithms (e.g. melspectrogra…
-
Hello :)
I have a question about the function "get_segmented_mels"
Why the range is not [start_frame_num, start_frame_num+5] but [start_frame_num-2, start_frame_num+2]?
and, Why did you use t…
-
What's the best way to calculate loudness per frame? And can we make it a function?
## TLDR;
Is it this?
``` python
S = abs(FFT(y))**2 # power spectrogram
weighting = A_weighting # weighti…
-
### 🐛 Describe the bug
We use the following script to convert MFCC to onnx (motivation: we've found that torchaudio MFCC implementation, librosa and especially cpp librosa implementations differ whil…
-
Hi @VVasanth,
thank you for you work and initiative. Indeed there's something missing in Java/Kotlin when dealing with audio signals.
I tried to use jliborsa hoping to get the same results as li…
-
Hi,
I am also running into the same issue as you guys. I am using a subset of the AVSpeech dataset.
The network seems to be hard stuck at 0.69. I once tried training it for a few million iteration…