Gustav von Zitzewitz

also interested in a trained model

@blackary thank you for that workaround. Is it possible to play the sound without showing the audio player widget at all?

For me (on macOS) it is able to create / save a .`wav` or `.aiff` file, but these are not readable / playable

@hinthornw this doesn't work for streaming responses though. Is there any way to make `OpenAICallbackHandler` work with `ChatOpenAI(streaming=True)` ? The issue is that `on_llm_end` is entered before the response is...

exactly the same issue but on `2,6 GHz 6-Core Intel Core i7 Macbook Pro` with `macOS Ventura 13.1`

would also be nice if someone could tell me how to properly call optimize_for_inference.py on the pre-trained ssd_mobilenet_v1_coco frozen Model. I was choosing image_tensor as Input Node and detection_boxes,detection_scores,num_detections,detection_classes as...

I tried it with installing ``` chromium chromium-driver ``` but that does not help

@acheong08 I am using `xvfb`, here is the full packages list i use to host: https://github.com/gustavz/jaivus/blob/main/packages.txt

nice! how do I use it, just pass my api key instead of the session key into `Chatbot`?

great, works for me now thanks!