DUSUNEN Nokta 68M v1
One compact Turkish model for punctuation restoration and true-casing. Nokta predicts both decisions in a single pass through 28 joint token labels, so deployment does not require a punctuation model followed by a second casing model.
Held-out results
The split is deterministic and leakage-resistant: all rows sharing a source URL remain in the same 98/1/1 train/validation/test bucket. The test bucket was not used for gradient updates or checkpoint selection.
| Metric | Majority baseline | DUSUNEN Nokta |
|---|---|---|
Punctuation macro F1, excluding NONE | 0.00% | 70.43% |
Casing macro F1, excluding LOWER | 0.00% | 86.98% |
| Joint-label macro F1 | 3.07% | 65.23% |
| Joint token accuracy | 62.35% | 94.04% |
| Exact full-sequence accuracy | 0.00% | 47.51% |
Punctuation token accuracy is 96.57% and casing
token accuracy is 97.00%. Machine-readable results and
class counts are included in this repository. dataset-audit.json records file
checksums, label distributions and zero source overlap across splits.
Try it
The repository includes inference.py, which handles Turkish dotted/dotless I,
subword-to-word alignment, punctuation marks and long-text chunking:
python inference.py "bugün istanbulda hava güzel mi yarın yağmur bekleniyor" --model GoktugD/DUSUNEN-Nokta-68M-v1
The checkpoint also loads directly with the standard Transformers API:
from transformers import AutoModelForTokenClassification, AutoTokenizer
model_id = "GoktugD/DUSUNEN-Nokta-68M-v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForTokenClassification.from_pretrained(model_id)
Validated ONNX
onnx/model.onnx is a lossless FP32 CPU export (270.8 MB).
Across 64 held-out examples, its token prediction
agreement with PyTorch was 100.000%. The recorded single-item
PyTorch/ONNX median-latency ratio was 0.65×; this release makes no
ONNX speedup claim. See onnx-validation.json for raw latency and numerical-parity
values. A separately tokenized variable-length input also achieved
100.000% prediction agreement.
Training and data
- Base model:
dbmdz/distilbert-base-turkish-cased(MIT), 68.1M parameters - Corpus: Cosmos Turkish Corpus v1.0 (CC BY 4.0)
- Examples: 146,936 train / 1,519 validation / 1,545 test
- Input length: at most 128 subword tokens
- Optimisation: AdamW, linear schedule, BF16, seed 42
- Hardware: NVIDIA GeForce RTX 3090 24 GB
- Training time: 725.7 seconds
- Exact programs:
prepare_nokta_dataset.py,train_nokta.py,export_nokta_onnx.py
Intended use and limitations
Nokta is intended for cleaning ASR output, subtitle drafts, search transcripts,
chat text and Turkish document preprocessing. It was trained on web text rather
than spontaneous speech transcripts, so domain punctuation can differ. Proper
names, stylised brands, mixed-language passages, URLs and deliberately unusual
casing remain difficult. The MIXED label restores acronym stems before an
apostrophe but cannot reconstruct every arbitrary character-level casing pattern.
Human review is required for legal, medical or other high-stakes documents.
Integrity
model.safetensorsSHA-256:ea24882907321293322bd2262e9684d16a2c45ff7f2a6bb89c579b8270150d5bonnx/model.onnxSHA-256:0444bd6786277999d4ce6612693d4e41ec56fffabd654441a04d1c562b2dc798
Developed and released by Göktuğ Düşünen.