Feature Extraction
Transformers
Safetensors
PyTorch
Russian
accentik
russian
accentuation
word-stress
custom-code
custom_code
Instructions to use TeraSpace/accentik with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TeraSpace/accentik with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="TeraSpace/accentik", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TeraSpace/accentik", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
6 days ago
-
Update Accentik to audio v3 with opt-in ё placement
Verified signatureImproved stress weights, parallel experimental ё head disabled by default, standalone Transformers code and CLI, matched tokenizer, corrected RUAccent-label provenance. Preserves the existing donation section and attribution license.daad4bf
7 days ago
-
Update README.md
Verified signaturec26a872 -
Release Accentik experimental context v2
Verified signatureFP32 safetensors, self-contained PyTorch/Transformers inference code, matched tokenizer, documented evaluation tradeoff and public-project attribution license.40f546e -
initial commit
Verified signature78f17ad