| """Run Accentik from Hugging Face or a downloaded model folder.""" |
| import argparse |
| from pathlib import Path |
|
|
| import torch |
| from transformers import AutoModel |
|
|
|
|
| def main(): |
| parser = argparse.ArgumentParser(description=__doc__) |
| parser.add_argument("--model", default="TeraSpace/accentik") |
| parser.add_argument("--revision", help="Optional pinned Hub commit") |
| parser.add_argument("--device", default="cpu") |
| parser.add_argument("--threads", type=int, default=2) |
| parser.add_argument("--restore-yo", action="store_true", help="Enable experimental е → ё placement") |
| parser.add_argument("--yo-threshold", type=float, help="Override the validation-selected ё threshold") |
| inputs = parser.add_mutually_exclusive_group(required=True) |
| inputs.add_argument("--text") |
| inputs.add_argument("--input", type=Path) |
| parser.add_argument("--output", type=Path) |
| args = parser.parse_args() |
| torch.set_num_threads(args.threads) |
| model = AutoModel.from_pretrained( |
| args.model, revision=args.revision, trust_remote_code=True, |
| ).to(args.device).eval() |
| text = args.text if args.text is not None else args.input.read_text(encoding="utf-8") |
| result = model.accentuate(text, restore_yo=args.restore_yo, yo_threshold=args.yo_threshold) |
| if args.output: |
| args.output.write_text(result, encoding="utf-8") |
| else: |
| print(result) |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
