-
Hi, first, thanks for the app. I hope you will add the following features.
- XML formatter,
- HTML Encoder/Decoder and
- Certificate Encoder/Decoder.
While using the app, I find few items are no…
-
Would you be open to supporting alternative base64 implementations? The one we've been using is https://github.com/segmentio/asm/tree/main/base64
It's significantly faster than the stdlib encoding,…
-
Thanks you for your excellent work!
The methods and results described in your paper are extremely valuable for my research. I am currently attempting to reproduce the results of your experiments.
…
-
### What is the problem this feature would solve?
JSON is large because contains redundant characters and isn't binary
### What is the feature you are proposing to solve the problem?
Implement nati…
ghost updated
1 month ago
-
This issue is not in response to a performance regression.
The method of performing cross-attention QKV computations introduced in #4942 could be improved. Because this issue relates to cross-atten…
-
I've revised the setting.py as below, but when running marker or marker_single, still it works under CPU mode.
----reivsion ---
line10:
class Settings(BaseSettings):
# General
TORCH_DEV…
-
Hi, nice that we get our own set of audio decoders.
I would love to see if we could add a simple speech encoder/decoder as well for when we use something like espnow to transfer speech audio, could t…
-
### Description
Automatic synthesis of hashable, encodable, and decodable proceeds without issue when containing a nested type with an unavailable conformance.
### Reproduction
The following …
-
Hi! When I try to run the simple server I get this error:
> config.json: 100%|████████████████████████████████████████████████████████████████████| 811/811 [00:00
-
**Describe the bug**
There is a mismatch between the `train.yaml` configuration file and the loaded model weights (`final.pt`) when using the Wenet pretrained model `wenetspeech_u2pp_conformer_exp`. …