-
I am attempting to train a model using your code.
In the base config file used in model training (e.g. when calling `sh train_run.sh`), a pretrained vocoder model seems to be required.
https://git…
-
Running through your pre-trained models, I found that generated audio does not exactly match the input in duration length. For example,
```
wav, sr = load_wav(os.path.join(a.input_wavs_dir, filname…
-
Have you try this on multi-speaker way ?
-
Hello, my input is
input (1, 257, 1, 2)
state_h (1, 31, 32)
state_c (1, 32, 32)
May I ask how I should create the correct Mat data type for ncnn inference?
-
So I'm using this with maskcyclegan voice conversion and I only have 1 hour of data of the speaker.
-
Hi @jaywalnut310 ,
Many thanks for your work!
As usual this is very thorough, open and inspiring.
In your paper you publish the GPU speed benchmarks:
> We measured the synchronized elapsed t…
-
Can I use this repo for training new tts model in another language?
How much hours of audio + transcripts do I need?
Does the text should have diacritical signs?
-
Hi
## The issue
I trained a model based on [Matcha TTS](https://github.com/shivammehta25/Matcha-TTS), and I tried to use Vocos with it. Unfortunately, vocoding using a checkpoint trained with th…
-
### Feature request
Ability to load only portions of models.
### Motivation
I'd like to only use a portion of a model, that has it's own defined class, without having to load in the entire model. S…
-
I found an implement for multiband hifigan which folk from this repo: https://github.com/rishikksh20/multiband-hifigan
Are there anyone have tried and benchmark for this?