-
For many corpora there are not multiple types of edges (or at least not for a certain annotation layer). For example, the Penn Treebank, WSJ, Switchboard, and also OntoNotes derived from the same unde…
-
It looks like we don't have many dialog tasks, especially for response generation.
This [webpage](https://github.com/sebastianruder/NLP-progress/blob/master/english/dialogue.md) contains a list of…
-
I am using inference mode. My test.csv file has 4.480 utterances. The output of preds_on_new.pkl is a list that is 12,342 items long. Am I doing something wrong?
-
@fungunga We tested the GeoBrowser with a csv file but it does not display anything on the map, only the first two columns of the csv file (attached, renamed to .txt because github would not attach it…
-
There are tools that require more than a single resource, e.g., tools that align audio with text, see
`curl -v -X POST -H 'content-type: multipart/form-data' -F LANGUAGE=deu-DE -F TEXT=@ -F SIGNAL=@ …
-
This diarization doesn't compare favorably with Whisper. Wondering if I'm missing something in call parameters or other
On this two minute video - https://www.youtube.com/watch?v=xbyEs7DJshw&ab_cha…
-
Due to an [issue](https://github.com/rwth-i6/returnn/issues/1450) that I have with a training that uses `FastBaumWelchLoss` that might be related to tensorflow, I wanted to try running the same setup …
-
Thanks for the great work! I'm also using FLAN for training, so I'm wondering how to include only tasks that are in Tasksource but not in FLAN.
-
On building my packages I'm using `sphinx-build` command with `-n` switch which shows warmings about missing references. These are not critical issues.
You can peak on fixes that kind of issues in …
-
I created an apptainer image with tf 2.13 and tried to run a training with `FastBaumWelchLoss`. It crashes in step 0 because the `get_sprint_automata_for_batch` op is not found.
```
EXCEPTION …