-
For accessibility reasons, we should have subtitles for all audio. There are various subtitle formats (.SRT for example), which have different features - need to investigate which ones work best for u…
fwild updated
4 months ago
-
# Task Name
Audio Segment Retrieval with Text Descriptions
## Task Objective
The objective is to retrieve specific parts of an audio clip based on textual descriptions. This represents a chal…
-
Defect:
Auto captioning attributes speech to the wrong person. When anyone speaks, Closed Captions only attributes their speech to the first person who enabled captioning during audio setup.
To R…
-
Add the audio transcription using whisper and image captioning with gpt4-v functions and implement them in the `gradio ui` notebook
-
# Task Name
Audio Tagging on AudioSet
## Task Objective
This task aims to give an audio some tags that best describe the audio. The model shall give several words (instead of a sentence in au…
-
Hi,sir:
I find the prompts for training and testing for audio event classification are different in the code. In the train task ”cla_label”, one example of the question is "Identify the audio’s n…
-
Hello,
I appreciate your excellent work and have a question regarding the testing process, specifically on how to ensure proper testing without falling into the trap of overfitting.
We conducted…
-
### New Feature Summary
With a number of recent development, I'd like to propose more vocab types that are subcategories of `TextDocument` (all names are tentative in the proposal)
- `Transcript`:…
-
when a media player displays media content with open captions, a cc control would not be needed. If no cc control is provided, 503.4 fails, but equivalent facilitation can be asserted.
-
As written, 1.2.5 [Audio Description (Prerecorded)] is superfluous.
• Guideline 1.2.5 is wholly included in guideline 1.2.3 (Audio Description and Media Alternative) which is a Level A). 1.2.5 is a …