-
Any idea on how to resolve this problem?
```
from SpecAugment import spec_augment_pytorch as spec_augment_l
import librosa
y, sr = librosa.load(dataset_audio_path.joinpath(audio_path), sr=160…
-
Hi all,
I think it's good timing to discuss a potential merging plan from [torchaudio-contrib](https://github.com/keunwoochoi/torchaudio-contrib) to here, especially because there's going to be new f…
-
Hi,
I want to extract 13 MFCC values from an audio file and I am using the newly added mfcc function like this -
`mfcc(nMFCC: 13, nFFT: 2048, hopLength: 512, sampleRate: 22050, melsCount: 128)`
…
-
Hello,
Could you please add the code to train wav2vec mapping in deepspeech?
Thank you.
-
### Reproducing code example:
Unfortunately I don't have a small reproducing example, but I can reproduce it most of the times in my code.
I call into `librosa.feature.melspectrogram` which …
-
Am trying to evaluate Essentia for standard and streaming case of FFT. To port from librosa to Essentia, i need to determine the right set of parameter input values to be passed in Essentia so that i …
-
Hi, Great job, I'm also interesting in AlignTTS, did u trained a such model successfully? Or even already got generated wave samples? :)
-
* librosaだと30日かかる勢い
* tensorflowでgpuを使えば早くなる？
* https://www.tensorflow.org/api_docs/python/tf/signal/mfccs_from_log_mel_spectrograms
-
Dear author,
This is a really nice project that generates much faster than wav2lip,
Now to generate a 30 second video, it only takes about 30 seconds,
My machine configuration: two 3090 graph…
-
I am run visualization and get error:
[INFO] model loaded.
Preprocess: 1% 12/889 [00:00 Tensor:
wav_tensor0 = (self.sox_effects).forward(wav_tensor, sample_rate, )
mel_tensor = (self.l…