Jilt Sebastian

confidence scores output from the LM

5

Is there a way to get the confidence scores (word/sub-word level) also as the output? with decode_beams, it is possible to get the time information for alignment purposes and KenLM...

Add play detect functionality to video

1

Awesome component! Thanks a lot! I am curious to know if a similar functionality can be applied to videos (not the same functionality). I embedded videos and detected the clicks...

Integrate HF PeFT adapter models in cTranslate or faster-whisper

2

@guillaumekln I am not sure if it is more apt for ctranslate2 but since the HF [Parameter efficient finetuning](https://github.com/openai/whisper/discussions/988) is also done for whisper for specific languages, I am posting...

Feature Request: Implement Static Cache and Quantization Techniques in CTranslate2

18

@minhthuc2502 @alexlnkp **Description** What type of cache is currently implemented in CTranslate2? Is it static or dynamic? Could we achieve a speed-up if the cache implementation is changed for the...

💡 [REQUEST] - Simultaneous multimodal inputs

25

### 起始日期 | Start Date _No response_ ### 实现PR | Implementation PR Can it already generate outputs if audio and video are provided at the same time? I have tried...