jackal

It's weird that the library support dumping to json or save to file but no API for importing back?

Inferencing result different from original whisper with GPU even when using same model

4

Is there any parameter that needs to be added into the implementation like in https://github.com/openai/whisper/tree/main/whisper/assets/multilingual ? I've tested all models and found the inferenced results are different compared to using...

Allow setting --prompt-delay to 0

4

Hi, can we have the --prompt-delay switch to allow setting to any value? Having a 3 seconds wait minimum in CI/CD doesn't really make much sense. If we want to...

[Feature request] Any chance to support export as a file in the command line switches?

2

dsnote currently supports some command line but there is no support for the export TTS audio in the switches. Would there be any chance to add this?

The video generated by LTXV 0.9.8 distilled makes human skin appear plastic

3

Hope this issue will be resolved in next version of the LTXV model. 0.9.8 is slightly faster than 0.9.7 but the outcome of human animation the skin looks plastic. Examples:...