-
https://github.com/mediar-ai/screenpipe/blob/7922064dda8c1882a3e52da0c30430fe4d641170/screenpipe-app-tauri/src-tauri/src/llm_sidecar.rs#L62
ollama on windows needs `OLLAMA_ORIGINS=*` because its CO…
-
I had the following frontend bug occur in current dev, but I did not manage to reproduce it unfortunately.
I transcribed "Jens Spahn's Credit Score is Very Good" from cccamp23. At timestamp 40:20 w…
-
there were no error about it
config:
```
[app]
video_source = "pexels"
pexels_api_keys = [ "",]
pixabay_api_keys = []
llm_provider = "openai"
ollama_base_url = ""
ollama_model_name = ""
open…
-
I'm trying to run the gpu accelerated version on a jetson nano. I'm not sure if it's supposed to work though.
I updated docker to the latest version. Unfortunately the gpu version of the package d…
peteh updated
11 months ago
-
**Suggestion Description**
Have your voice range auto set to the 2nd (Normal) option when you spawn in.
**Reason**
Currently you spawn in with your voice set to whispering. A lot of times I forge…
-
Hi, I've had some files which have failed to transcribe and that have produced error logs in the whishper_data\logs directory but haven't had an error message on the web client and so aren't able to b…
-
There are a few issues talking about chat filtering so I've decided to just make a new, single topic for it all. The new FrankerFaceZ chat filtering system is being redesigned to be much easier to ext…
-
Running on Windows 11,
CUDA (NVidia RTX 3090)
python 3.10.6
Server is run with `subsai-webui --server.maxUploadSize 50000` in case that's relevant.
using `faster-whisper` and `large-v2`
Try…
-
Recently made public:
https://openai.com/blog/whisper/
https://github.com/openai/whisper
Interesting, they have some multilingual models that can be used for multiple languages without fine tunin…
-
line 8, in
sys.exit(main())
File "/Users/wesley/miniconda3/lib/python3.9/site-packages/yt_whisper/cli.py", line 49, in main
result = model.transcribe(audio_path, **args)
File "/Users/…