-
Thanks a lot for your great contribution, but I'm having some issues reproducing your work. For the metadata part in the code base, does the source data contained inside come from the Clotho-AQA datas…
-
First of all, thanks for your code!
I wonder how you train AC+Clotho+WavCaps together, I have seen that different datasets are fed into the “AudioCaptionDataset” module separately in your code .So I …
-
Hi, thank you for publishing wavcaps! it is really useful.
I am trying to reproduce the results using HTSAT-BART using the code pretrain.py. But I got the following errors:
- in **pretrain.yaml** in…
-
Hi,
I try to reprocess Clotho and AudioCaps dataset, and calculate the retrieval metrics for audio and text. But when I processed the datas as you released and run the eval code. There is an error, _…
-
May I ask about how to access the dataset while using the given code?
In the main.py, it seems to use the following line to copy dataset from aws service:
f"aws s3 cp s3://s-laion-audio/webdataset…
-
The csv file _clotho_captions_development.csv_ contains some entries with trailing spaces, such as [ typical neighborhood in Porto.wav], which should be [typical neighborhood in Porto.wav], without th…
-
Hello,
I just encountered this error today. Everything worked fine yesterday and now when I try to use the vggish embeddings I get this error:
```urllib.error.URLError: ```
This is what I've tr…
-
I am trying to reproduce the results of "CNN14+BERT", but the obtained results are significantly different from that shown in the tech report. I would like to know if I did anything wrong.
The conf…
-
When trying to train the MMT model, the error is popping up. What is the solution to this?
![1](https://user-images.githubusercontent.com/79996558/176207806-6463cc14-db10-4ed6-a94b-bf907ab60e7b.p…
-
I only changed the line186-193 because we need audio input function `get_wds_dataset`. It always stuck when I set num_worker=2. https://github.com/mlfoundations/open_clip/blob/main/src/training/data.p…