Bardo-Konrad
Bardo-Konrad
My predict.py: ``` from utils.config_manager import ConfigManager from utils.audio import Audio from scipy.io.wavfile import write config_loader = ConfigManager('ljspeech_autoregressive_transformer\standard', model_kind='autoregressive') audio = Audio(config_loader.config) model = config_loader.load_model() was = 'President Trump met...
- are `fsID `and `salience `necessary and if so, what do they mean? - where to set the filename of the csv in the `metadata `subfolder? - I get `ValueError:...
Please offer a docker image
**🚀 Feature Description** Appropriate intonation using xtts_v2 und voice cloning **Solution** There is a certain structure to intonation that gives a natural flow, the same with using pauses. So the...
### Describe the bug Sometimes the speech pauses then the speaker continues but it's neither written nor is it any language, but it's clearly the same speaker. Unless you want...
I access ollama using the python library. It communicates well but after some exchanges I always get the following. It seems that I need to reset ollama via python or...
I get endless output like this ``` Parsing nodes: 100%|██████████████████████████████████████████████████████████████████████████| 1/1 [00:00
How does this compare to coqui?
I used it for a 10 minute recording and it kept on repeating many sentences and did not detect the rest. Fortunately it saved it as wav in temp, so...
My approach Use `aliceVision_split360Images.exe --splitMode equirectangular --equirectangularNbSplits 8 --equirectangularSplitResolution 768 --fov 90.0` Result is random. Some datasets are found using `exhaustive matching`, many others are not. Using it in `meshroom`...