-
Is there a way to use Spanish instead of English, I recently setup the code, I will be trying to do it but any help on this would be awesome.
-
Dataset https://huggingface.co/datasets/Muennighoff/flores200 has more than 40,000 configs. It's too much for our infrastructure for now. We should set a limit on it.
-
Environment:
- tokenizers: 0.13.3
- transformers: 4.28.1
- OS: Breaks on both Linux and Windows
Reproduction:
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_p…
-
When I give some ambient sound as input to fast whisper in Chinese language, it will give abnormal results like below:
请不吝点赞 订阅 转发 打赏支持明镜与点点栏目
谢谢观看 下集再见
谢谢观看 欢迎订阅我的频道
字幕由Amara.org社区提供
-
Hi,
I tried to run prepare_data.py with the following config but met duplication error during dictionary loading. I noticed the dictionary size is more than doubled from the pretrained SPM-200 voca…
-
Accelerate makes it easy to load a model on multiple GPUs with `device_map="auto"`. This in turn allows users to train model with naive model parallelism if they have several GPUs.
A problem that h…
-
I tried up/downgrading cuda and pytorch, but i keep getting this type error
### Traceback
ERROR: [web] TypeError: '
-
## 🐛 Bug
I am trying to install Fairseq from the source on colab and it seems to be running into import errors.
[Here](https://colab.research.google.com/drive/1EdFPAvlG69hpTsKxDPKg2dreMtI_LK…
-
Hi,
I am a researcher working on Low resource languages native to sri lanka (which is Sinhala and Tamil). NLLB mined dataset is a excellent start point for us. So i am using the instructions provided…
-
I have had this setup on Google Colab with GPU accelerated runtime. But it doesnt seem to leverage the GPU while using POST request.
Is my understanding correct that only in batch mode when used v…