| --- |
| language: |
| - en |
| - lv |
| tags: |
| - translation |
| license: cc-by-4.0 |
| datasets: |
| - quickmt/quickmt-train.lv-en |
| model-index: |
| - name: quickmt-lv-en |
| results: |
| - task: |
| name: Translation lav-eng |
| type: translation |
| args: lav-eng |
| dataset: |
| name: flores101-devtest |
| type: flores_101 |
| args: lvs_Latn eng_Latn devtest |
| metrics: |
| - name: BLEU |
| type: bleu |
| value: 35.3 |
| - name: CHRF |
| type: chrf |
| value: 62.91 |
| - name: COMET |
| type: comet |
| value: 86.98 |
| --- |
| |
| <a href="https://huggingface.co/spaces/quickmt/quickmt-gui"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-lg-dark.svg" alt="Open in Spaces"></a> |
|
|
| # `quickmt-lv-en` Neural Machine Translation Model |
|
|
| `quickmt-lv-en` is a reasonably fast and reasonably accurate neural machine translation model for translation from `lv` into `en`. |
|
|
|
|
| ## Try it on our Huggingface Space |
|
|
| Give it a try before downloading here: https://huggingface.co/spaces/quickmt/QuickMT-gui |
|
|
|
|
| ## Model Information |
|
|
| * Trained using [`eole`](https://github.com/eole-nlp/eole) |
| * 200M parameter transformer 'big' with 8 encoder layers and 2 decoder layers |
| * 32k separate Sentencepiece vocabs |
| * Expested for fast inference to [CTranslate2](https://github.com/OpenNMT/CTranslate2) format |
| * Training data: https://huggingface.co/datasets/quickmt/quickmt-train.lv-en/tree/main |
|
|
| See the `eole` model configuration in this repository for further details and the `eole-model` for the raw `eole` (pytorch) model. |
|
|
|
|
| ## Usage with `quickmt` |
|
|
| You must install the Nvidia cuda toolkit first, if you want to do GPU inference. |
|
|
| Next, install the `quickmt` [python library](github.com/quickmt/quickmt). |
|
|
| ```bash |
| git clone https://github.com/quickmt/quickmt.git |
| pip install ./quickmt/ |
| ``` |
|
|
| Finally, use the model in python: |
|
|
| ```python |
| from quickmt import Translator |
| from huggingface_hub import snapshot_download |
| |
| # Download Model (if not downloaded already) and return path to local model |
| # Device is either 'auto', 'cpu' or 'cuda' |
| t = Translator( |
| snapshot_download("quickmt/quickmt-lv-en", ignore_patterns="eole-model/*"), |
| device="cpu" |
| ) |
| |
| # Translate - set beam size to 1 for faster speed (but lower quality) |
| sample_text = 'Dr Ehud Ur, będący profesorem medycyny na Uniwersytecie Dalhousie w Halifaxie w Nowej Szkocji oraz przewodniczącym oddziału klinicznego i naukowego Kanadyjskiego Stowarzyszenia Cukrzycy, przestrzegł, iż badania nadal dopiero się zaczynają.' |
| |
| t(sample_text, beam_size=5) |
| ``` |
|
|
| > 'Dr. Ehud Ur, a professor of medicine at Dalhousie University in Halifax, Nova Scotia and chairman of the clinical and scientific division of the Canadian Diabetes Association, warned that research is still just beginning.' |
|
|
| ```python |
| # Get alternative translations by sampling |
| # You can pass any cTranslate2 `translate_batch` arguments |
| t([sample_text], sampling_temperature=1.2, beam_size=1, sampling_topk=50, sampling_topp=0.9) |
| ``` |
|
|
| > 'Professor of Medicine at Dalhous University Halifax in Nova Scotia, MD and Chair of the Canadian Diabetes Association’s Clinical and Scientific Division, cautioned that research is just beginning.' |
|
|
| The model is in `ctranslate2` format, and the tokenizers are `sentencepiece`, so you can use `ctranslate2` directly instead of through `quickmt`. It is also possible to get this model to work with e.g. [LibreTranslate](https://libretranslate.com/) which also uses `ctranslate2` and `sentencepiece`. A model in safetensors format to be used with `eole` is also provided. |
|
|
|
|
| ## Metrics |
|
|
| `bleu` and `chrf2` are calculated with [sacrebleu](https://github.com/mjpost/sacrebleu) on the [Flores200 `devtest` test set](https://huggingface.co/datasets/facebook/flores) ("pol_Latn"->"eng_Latn"). `comet22` with the [`comet`](https://github.com/Unbabel/COMET) library and the [default model](https://huggingface.co/Unbabel/wmt22-comet-da). "Time (s)" is the time in seconds to translate the flores-devtest dataset (1012 sentences) on an RTX 4070s GPU with batch size 32 (faster speed is possible using a larger batch size). |
|
|
| | | bleu | chrf2 | comet22 | Time (s) | |
| |:---------------------------------|-------:|--------:|----------:|-----------:| |
| | quickmt/quickmt-lv-en | 35.3 | 62.91 | 86.98 | 1.39 | |
| | Helsinki-NLP/opus-mt-lv-en | 30.86 | 59.56 | 85.23 | 3.61 | |
| | facebook/nllb-200-distilled-600M | 32.14 | 59.13 | 84.62 | 21.92 | |
| | facebook/nllb-200-distilled-1.3B | 36.63 | 62.59 | 86.86 | 37.95 | |
| | facebook/m2m100_418M | 27.01 | 56.61 | 81.66 | 18.57 | |
| | facebook/m2m100_1.2B | 33.61 | 61.31 | 86.15 | 35.87 | |
|
|
