Mixomo
Mixomo
hello. when i try to run the downloaded model i get this error.... it happens to me with several models regardless if they are from civitai or hugginface. (they are...
For the new version: Crepe support for F0 extraction in training and inference. Thank you
I have an idea for the future version: The possibility to train the model with the singer's expressivity by analyzing and extracting the RMS values. This would also allow to...
You see, when I want to generate an audio using Harvest, (inference stage), the Gradio interface keeps processing until it ends in the mentioned error. However, the audio is generated...
would it be possible to add a third route to a model C to combine with models A and B? I tried to modify the section in infer-web.py and managed...
Hello, this is something very strange that has been happening to me more and more frequently. When fine tuning a tacotron model, the end result sounds distorted. I have trained...
Hi, I see that the PRIORS datasets are synthetic. I plan to replace them with more natural sounding datasets (either synthetic and/or human). This will help for a better and...
Hello! Is it possible to run Whisper from GPU? When transcribing the audios, I see that it uses my CPU and takes forever. I haven't seen the option to switch...
Hello, I'm trying to train a custom model with a Spanish dataset; however, when I ran the training command (!python preprocess_text.py --metadata /content/metadata.list), I received the next error: Traceback (most...
**🚀 Feature Description** Possibility of using a fixed seed for inference in XTTS V2, so that the consistency and robustness of the model could be better evaluated with different reference...