-
# Task Name
Answering a Spoken Question given a spoken document
## Task Objective
The goal of QA is to find the answer span in a spoken document given a spoken question. The answer span is de…
-
# Task Name
Spoken Question Answering
## Task Objective
In this task, when the model is given a spoken document, it needs to find the answer to a text-based question. The answer to each quest…
XMHZZ updated
3 weeks ago
-
# Task Name
Question Answering Grounded by Spoken Speech
## Task Objective
In this task, the model is given a pair of context and question where context is in speech format and the question i…
-
**Is your feature request related to a problem? Please describe.**
As a user I want to know which languages are spoken at a POI, such that I know whether I need to bring a translator or not.
**Des…
-
# Task Name
Spoken digit arithmetic
## Task Objective
This task requires the model to perform basic arithmetic calculation based on the text instruction and the two input audio utterances. Each u…
-
While speaking, iOS generates multiple versions of the recognized text. For example if you say "3+4" it will first generate `Three` and then replace that with `3+4`. We are not properly deleting the `…
-
# Task Name
Spoken digit recognition - AudioMNIST
## Task Objective
The task's objective is to classify audio samples of spoken digits (0-9) into their corresponding Arabic number representat…
-
Hi @AmitMY
Continuing the problem from previous issues and PRs,
After I can create a dummy lexicon and get a csv file like the image below
![image](https://github.com/sign-language-processing/spok…
-
Hi.
It would by really useful if we could return the spoken language in the audio, something [like this](https://github.com/ggerganov/whisper.cpp/blob/2948c740a2bf43190b8e3badb6f1e147f11f96d1/examp…
-
Hello,
I'd like to mention a partial classification error for Alsatian. In Glottolog, Alsatian is classified in the Alemannic dialect family. This is only partially correct, as the term Alsatian i…