-
I tried to reproduce the results of data2vec using the open source configuration, but the performance was rather poor. So I compared the parameters in the public model [audio_base_ls.pt](https://dl.fb…
-
### Feature request
As pointed out in https://github.com/huggingface/transformers/pull/27742, some image processors might need a correction on the default interpolation method being used (resamplin…
-
报错如图,
是否是因为我的decode.sh编写错误呢,内容如下:
. ./path.sh || exit 1
data=/home/ubuntu/Desktop/kaldi/kaldi-trunk/egs/yesno/s5/test_wav
model=/home/ubuntu/Desktop/voice/telespeech-asr1.0/finetune_large_kesp…
-
Hi, do you remember where there was a great gap between the +bpp and -bpp model according to their training loss?
-
### Feature request
Some of our models interpolate its positional embeddings, enabling pretrained checkpoints to be used on different input resolutions. For example, [here in ViT](https://github.co…
-
### Feature request
Addition of TF implementation of BEiT
### Motivation
I have always seen that there is a discrepancy in the availability of models for PyTorch and the models available in Tensor…
-
Not sure if any other work has implemented and investigated this approach of Focal Masking before but [1] combines Focal Masking and Random Masking to improve self-supervised pre-training for learning…
-
Hello,
I am very new to HuggingFace and machine learning in general. I understand that the Blip model is not supported for conversion to coreml. Can this be added to this repo? If not, Is there a …
-
OS: linux
Python/C++ Version:3.8
Package Version:pytorch 2.0.1、torchaudio 2.0.2、modelscope 1.7.1、funasr version 0.6.9
Model:aishell2/pretrain
Command:bash run.sh
Error log:AttributeError: 'TriSta…
-
### System Info / 系統信息
CUDA Version: 12.2
Transformers:4.45.1
Python:3.10.12
操作系统:ubuntu
vllm:0.6.2
### Who can help? / 谁可以帮助到您?
_No response_
### Information / 问题信息
- [X] The official exa…