BART-base fine-tuned for English -> ASL gloss (ASLG-PC12)
facebook/bart-base
fine-tuned on the training split of the ASLG-PC12 English-ASL gloss parallel
corpus. Input is a lowercased English sentence; output is an upper-case ASL gloss sequence in the
corpus's conventions (
X-
pronouns,
DESC-
modifiers).
This model is one of the systems in a small project comparing grammar-constrained decoding
(xgrammar) with unconstrained decoding for gloss generation. Code, grammars and evaluation scripts:
https://github.com/TheRealGioviok/asl-gloss-nlp
Training
Base model
facebook/bart-base
Data
training split of the
Kaggle redistribution of ASLG-PC12
(87,710 pairs, no official split; deduplicated and re-split 80/10/10 with seed 42 in the project)
Epochs
3
Effective batch size
32
Learning rate
3e-5
Max length
128 tokens (source and target)
Steps
6,084
Weights are stored in fp16 (the evaluation in the project also ran in fp16).
Results (1,000-sentence test sample, greedy decoding)
Decoding
BLEU
chrF
Exact match
Sequence validity
Unconstrained
76.7
93.3
44.5%
48.6%
Constrained (grammar v3)
73.2
85.9
42.8%
100%
Constrained + copy rule (v3)
74.1
86.3
44.5%
100%
"Sequence validity" is the share of outputs whose every token is in the closed gloss vocabulary.
Usage
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
repo = "425GMM/bart-base-aslg-gloss"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForSeq2SeqLM.from_pretrained(repo)
src = "we should behave outside european waters in just the same way as we do at home ."
ids = tok(src, return_tensors="pt")
out = model.generate(**ids, max_new_tokens=128)
print(tok.decode(out[0], skip_special_tokens=True))
Source sentences in ASLG-PC12 are lowercased with spaces before punctuation; feed the model text in
the same form.
Limitations
ASLG-PC12 glosses are rule-generated from Europarl text, not produced by signers. The model learns
those rules; it is not a general English-to-ASL translator and scores do not transfer to
human-annotated gloss corpora.
Runs of 425GMM bart-base-aslg-gloss on huggingface.co
182
Total runs
-6
24-hour runs
-16
3-day runs
-30
7-day runs
-235
30-day runs
More Information About bart-base-aslg-gloss huggingface.co Model
bart-base-aslg-gloss huggingface.co is an AI model on huggingface.co that provides bart-base-aslg-gloss's model effect (), which can be used instantly with this 425GMM bart-base-aslg-gloss model. huggingface.co supports a free trial of the bart-base-aslg-gloss model, and also provides paid use of the bart-base-aslg-gloss. Support call bart-base-aslg-gloss model through api, including Node.js, Python, http.
bart-base-aslg-gloss huggingface.co is an online trial and call api platform, which integrates bart-base-aslg-gloss's modeling effects, including api services, and provides a free online trial of bart-base-aslg-gloss, you can try bart-base-aslg-gloss online for free by clicking the link below.
425GMM bart-base-aslg-gloss online free url in huggingface.co:
bart-base-aslg-gloss is an open source model from GitHub that offers a free installation service, and any user can find bart-base-aslg-gloss on GitHub to install. At the same time, huggingface.co provides the effect of bart-base-aslg-gloss install, users can directly use bart-base-aslg-gloss installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
bart-base-aslg-gloss install url in huggingface.co: