-
Feature request. Would it be possible to add elevenlabs_tts and whisper_stt to the discord bot so you could talk to it and have it reply with voice? I know these features work with the web ui.
-
Found in code here:
https://github.com/google/mediapipe/blob/3a93a5d5d3f90ba3863f14ef4b0a4fc01505d035/mediapipe/web/graph_runner/graph_runner.ts#L929
I'm not sure how the ModuleFactory is defined,…
-
This is an idea that just popped up, while I was trying to search something.
Maybe we can integrate whisper.cpp or something like that, for interaction? It would be awesome if the Assistant can se…
-
The code examples in the README do not make it obvious how to set the language of the audio to transcribe.
The default settings create garbled english text if the audio language is different.
-
I executed the command `python app.py` and provided a YouTube video link through the web interface, but received the following error message:
```
Traceback (most recent call last):
File "C:\Users…
-
I think it would be great to be able to leverage WhisperX and speaker diarization. Any plans to do this?
https://github.com/m-bain/whisperX
-
## **Description**
Transcription fails using GPU support on .mp4 file with Nvidia GTX 980 because of unsupported compute type.
Is there a way to manually change the compute type?
Error: **ValueEr…
-
**Which OS are you using?** Windows 11
- OS: [e.g. iOS or Windows.. If you are using Google Colab, just Colab.]
This is what I get after when I run start-web-ui.bat
Traceback (most recen…
-
## Goal
- 8th October demo at our event
- Intended as a server-side demo: learnings to be then applied in https://github.com/janhq/jan/issues/3488 (Sprint 22-23)
## Questions
- What data can we col…
-
**Describe the bug**
Audio messages fail to be reproduced on iPhone and iPad. Speech-to-text and text-to-speech tool calls work, as can be seen in the CoT but audios cannot be heard. It appears "Erro…