-
## Question
Is it possible to execute ```core/audio_utils.melSpectrogram``` in the browser (or mobile)?
## Background of question
I develop mobile app with React Native and look for log mel…
-
I have trained an audio classification model using Keras & Tensorflow and converted it to Tensorflow lite, it is converted fine but when I run on Android I get this error:
```
Process: org.tensor…
-
> They are my prepared training list.
> each line looks like this:
> spectrogram_path acosutic_frame_number phone_number
> for example:
> /home/jxzhang/Documents/DataSets/VCTK/spec/p225/log-spec-p…
-
Thanks for your work !
I use `tts` melspectrogram output directly as the input of r9y9's [wavenet_vocoder](https://github.com/r9y9/wavenet_vocoder) pretrained model in order to get better quality, b…
-
Hi,
I am trying to train a Tacotron2 model in Hindi. I have my own 25 hour single speaker cleaned dataset. I'm using the following configuration.
{
"model": "Tacotron2",
"run_name": "h…
-
It might not be a bug, but I have noticed the same reference .wav yields different results during test and inference times. When training and testing the same sentence using the same wav file, the spe…
-
Most of librosa only supports monophonic audio. But for many of the analyses we'd like to do, stereo or multi-channel support would be very useful and not all that difficult at this point.
This is…
-
Hi Keunwoochoi. Not exactly an issue, but I am attempting to do audio source separation using the audio mix as input and the stem as output. Since the output audio signals are so large (44100 samples …
-
This dataset is really useful. Is there any recipe using ESPNet to extract features?
-
Hi!
So, I am trying to do inference on VCTK with your pretrained model and getting some inconsistencies with resutls [here](https://lmnt.com/assets/wavegrad/24kHz/)
I am doing the following steps:
…