-
In your transcriber.py, line 102, you obtain the melspectrogram by using
```python
mel = melspectrogram(audio_label.reshape(-1, audio_label.shape[-1])[:, :-1]).transpose(-1, -2)
```
The `audio_l…
-
Hi,
Thanks for sharing this great work. I have just one question:
During the training of all models, did you face a problem of mismatched energy levels between the target and generated speech wave…
-
Can you please add?I want to learn.
-
I have trained a new waveglow model for my language, but I cant load it into Tacotron2 `inference.ipynb` file to run test. It return this error:
`AttributeError: 'WN' object has no attribute 'cond_la…
-
This is not a real issue, it's simply an example of the output when run on the conda environment I have been using to develop gatherup. The purpose is simply to give a quick idea of what the formatt…
-
>>> openl3.models._construct_mel128_audio_network()
WARNING:tensorflow:From /home/zhaos/anaconda3/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:66: The name tf.get_default_graph is …
-
#### Description
From my vague understanding of MFCC, the DCT is needed to compute the final values. However, according to the docs at [https://librosa.github.io/librosa/generated/librosa.f…
-
Hi, thanks for the code !
If I'm not mistaken, part of the code comes from `librosa`'s source code and the corresponding license is not included.
It would make sense to add it IMO
-
Hello everyone!
I mentioned that the mel spectrogram generated by the Tacotron model (obtained with
```
waveform, alignment, decoder_outputs, postnet_output, stop_tokens = synthesis(
mo…
vcjob updated
4 years ago
-
is it not possible to detect the environmental sounds in real time? like can I attach a microphone to detect it in real time?
thanks.