-
english_mfcc = np.array([]).reshape(0, num_mfcc_features)
for file in glob.glob(codePath + 'english/*.npy'):
at this line you used .npy what this mean can u share it and tell how u created it.
-
The MFCC conversion routines could be checked against the [torchaudio.transforms](https://pytorch.org/audio/stable/transforms.html#mfcc) equivalent to see whether they match (possibly after tweaking p…
-
Considering the workflow for audio recording and feature extraction is clear as per #1 , we can proceed towards the POC for the same task but on an ESP32 or Arduino board.
The previous POC can be em…
-
I would like to use a data generator and tune epochs and batch size of a BLSTM Model. How do I pass the generator to the trial function?
Batch Generator :
```
def batch_generator(ids, batch_size…
-
Currently it seems that the `.. only_in:: sc`` functionality only works in the discussion section. It would be wonderful for it to also be available in the `:control:` sections to enable something lik…
-
In order for the wake word to work on Android we need:
- Write the inference using TF Lite.
- There's already some code for processing this in Rust [Precise RS](https://github.com/sheosi/preci…
-
With MFCC features?
-
```
File "code/rnn_example.py", line 20, in
X = np.load('top_3_100_split_mfcc.npy')
File "/usr/local/lib/python2.7/site-packages/numpy/lib/npyio.py", line 370, in load
fid = open(file…
-
-
Implement feature extraction independently from the training part: Since this part takes some time, it should be done once so that multiple trainings can be done without computing them each time.
i…