-
While our [draft charter](https://www.w3.org/2023/03/proposed-webmachinelearning-charter.html) says that the group:
> priority on building blocks required by well-known model architectures such as re…
-
In [`7d8f096`](https://github.com/OpenVoiceOS/status/commit/7d8f0966a139624d990e982a20f498a5947ae5cf
), Translator - NLLB - Ziggyai (https://ovosnllb.ziggyai.online/status) was **down**:
- HTTP code: …
-
In [`1b9e0bc`](https://github.com/OpenVoiceOS/status/commit/1b9e0bcb9712d207ff47e0b2c56ffdc80d39a335
), Translator - NLLB - Ziggyai (https://ovosnllb.ziggyai.online/status) was **down**:
- HTTP code: …
-
Currently files listed in a config.yml file for calculating alignments are listed in the corpus-stats.csv file without the "iso-" prefix. When I wish to include the best scoring file in an experiment …
-
hello ! Can I replace tokenizer's vocab to get a new tokenizer?
ex:
```python
with open("/data/hyxu/codes/LLMPruner/model/en-tr/nllb-200-distilled-600M/tokenizer.json") as f:
tokenizer_json = …
-
We fine tune HF models using mixed precision (`fp16`). In spite of this, I believe that models like NLLB are still loaded using `torch.float32` weights. We should try forcing the model to load using `…
-
### General informations
Self hosted web translate api with plugins available such as NLLB, Bloomz, Libretranslate, OpenAI and others.
### API basic informations
- [ ] This translation engin…
-
**Describe the bug**
Translation into a language with non-Latin (i.e. non-ASCII-encodable, e.g. Cyrillic) script fails due to an attempt to write into a file in `ascii` encoding.
**To Reproduce**
…
-
Problem description for possible scientific research and more details: [Alternative Spelling rules in some languages for benchmarking embeddings models](https://github.com/facebookresearch/flores/issu…
-
Is it possible to support GPU? I found out that CTranslate2 supports GPU. Does it support GPU to respond faster?