Justin Uberti
Justin Uberti
Use captureElement to create a video stream from a tag with canned video, instead of using the webcam. This will ensure a more accurate test since we know the content...
Mobile Client Error Error: TextEncoder is required for this module to work in the browser ERROR Invariant Violation: Failed to call into JavaScript module method AppRegistry.runApplication(). Module has not been...
Relevant to #8
Quantize Ultravox to fp8 and determine how this affects the model's inference performance as well as speed. This would entail - adding quantization to ultravox/infer - adding a flag to...
Apply ASR (e.g., Whisper) to an existing speech dataset to establish word-level timings, and add said timings as an additional column for the dataset. With this new column, add an...
Add a notebook file showing how to load and inference the model.