Closed dr3nan closed 1 year ago
Run the app directly from the Terminal to see error logs:
/Applications/Cheetah.app/Contents/MacOS/Cheetah
What do you see?
Here it is when I select device
Here at launch
What about when you click Answer?
I have this issue too, when I click answer nothing new appears in terminal or in the app. My logs look identical to @dr3nan.
whisper_model_load: loading model
whisper_model_load: n_vocab = 51864
whisper_model_load: n_audio_ctx = 1500
whisper_model_load: n_audio_state = 1024
whisper_model_load: n_audio_head = 16
whisper_model_load: n_audio_layer = 24
whisper_model_load: n_text_ctx = 448
whisper_model_load: n_text_state = 1024
whisper_model_load: n_text_head = 16
whisper_model_load: n_text_layer = 24
whisper_model_load: n_mels = 80
whisper_model_load: f16 = 1
whisper_model_load: type = 4
whisper_model_load: mem required = 1725.00 MB (+ 43.00 MB per decoder)
whisper_model_load: adding 1607 extra tokens
whisper_model_load: model ctx = 1462.35 MB
whisper_model_load: model size = 1462.12 MB
whisper_init_state: kv self size = 42.00 MB
whisper_init_state: kv cross size = 140.62 MB
What about when you click Answer?
Well, nothing ever really happens besides transcribing. If I wait till the transcription is finished and press the answer button, nothing happens. A short spinner loader happens, about 1000ms +-.
Can't even highlight text from transcription.
Released a new version that should now show an error message when this happens: https://github.com/leetcode-mafia/cheetah/releases/tag/v1.1
Released a new version that should now show an error message when this happens: https://github.com/leetcode-mafia/cheetah/releases/tag/v1.1
here is the error code
The same issue is happening with me
Do you have access to GPT-4?
Yes , I do
I downloaded the new version and now I'm getting this new error message:
i couldn't understand how to run the project, any help?
It's working now, god bless you man @leetcode-mafia , I had to pay for the Open AI API, I thought it worked with the Chat GPT Plus subscription but it's different, for me it doesn't work with gpt-4, it says the model is unavailable
Hello there,
I have everything set and the prompts are being transcripted into the app, but once I press on Analise, it does nothing.
Is there a need to have SIP off or something?
Great work btw