-
Siddhartha Brahma
https://www.aclweb.org/anthology/P19-1142/
* RNNベースの言語モデルの性能向上を、新しい正規化手法によって実現
* 過去にも正規化の工夫をする研究はあった
* RNNベースでは過去の予測(出力)が次の単語の予測に用いられる
* 対称性のある構造
* Past Decode Regula…
-
Hello. i am using Batch trancription.
some of my audios dont have any speech in the first 30 or even 60 or even 300 seconds.
i want the language detection to happen in the time range 300-330 secon…
-
-
I created a prototype using Whisper-Turbo, which performed well and processed files quickly. I was using an 8-bit quantized medium model (specifically this one: https://rmbl.us/whisper-turbo/medium-q8…
-
Your dataset makes sign language tasks closer to real application scenarios. Thank you for your contribution!
In real environments, in addition to recognition tasks, we also need to face translation …
-
### Willingness to contribute
No. I cannot contribute this feature at this time.
### Proposal Summary
It's just to avoid new users having the problem that I went through which is detailed in [issue…
-
### Feature request
Extend the `sft_vlm.py` script to support the new Molmo models from AllenAI: https://huggingface.co/collections/allenai/molmo-66f379e6fe3b8ef090a8ca19
Paper: https://arxiv.org/…
-
Attention mechanisms are widely used in deep learning models, particularly in large language models. And a flexible attention kernel can help users to build accelerated language models conveniently on…
-
1)
/Video-XL/videoxl/videoxl/train/llava_trainer.py", line 252, in compute_loss
if "retrieval_span" in inputs:
TypeError: argument of type 'NoneType' is not iterable
Traceback (most recent ca…
-
https://docs.github.com/en/rest/copilot/copilot-metrics?apiVersion=2022-11-28#get-copilot-metrics-for-an-enterprise
🚀 Now Available: GitHub Copilot Metrics API in General Availability! 🚀
We’re thr…