Token Classification
Transformers
ONNX
Safetensors
English
Japanese
Chinese
bert
anime
filename-parsing
Eval Results (legacy)
Instructions to use ModerRAS/AniFileBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModerRAS/AniFileBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="ModerRAS/AniFileBERT", device_map="auto")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("ModerRAS/AniFileBERT") model = AutoModelForTokenClassification.from_pretrained("ModerRAS/AniFileBERT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 5,370 Bytes
7509455 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | """Tests for the DMHY annotation pipeline interchange validator."""
from __future__ import annotations
import json
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path
class DmhyAnnotationPipelineValidatorTests(unittest.TestCase):
def write_jsonl(self, path: Path, rows: list[dict]) -> None:
path.write_text(
"".join(json.dumps(row, ensure_ascii=False) + "\n" for row in rows),
encoding="utf-8",
)
def unit(self, terminal_ids: list[str] | None = None) -> dict:
return {
"unit_id": "u-1",
"source_kind": "prefix_tree",
"source_id": "t-1",
"terminal_ids": terminal_ids or ["t-1", "t-2"],
"weight": 2,
"context": {
"prefixes": ["Show - 01"],
"digit_skeletons": ["Show - ##"],
"edge_labels": [" [1080p]"],
"notes": None,
},
"examples": {
"values": ["Show - 01 [1080p].mkv"],
"suffixes": [" [1080p]"],
},
"expected_output": {"schema_version": "dmhy-annotation-v1"},
}
def patch(self, terminal_ids: list[str] | None = None, status: str = "ok") -> dict:
return {
"unit_id": "u-1",
"terminal_ids": terminal_ids or ["t-1", "t-2"],
"annotation": {
"episode_title_suffixes": [],
"media_suffixes": ["[1080p]"],
"title_candidates": [],
"llm_label": None,
"notes": "clean",
},
"status": status,
"errors": [],
}
def run_cli(self, *args: str) -> subprocess.CompletedProcess[str]:
return subprocess.run(
[sys.executable, "-m", "tools.validate_dmhy_annotation_pipeline", *args],
check=False,
capture_output=True,
text=True,
)
def test_validate_units_and_manifest(self) -> None:
with tempfile.TemporaryDirectory() as tmpdir:
tmp = Path(tmpdir)
units = tmp / "units.jsonl"
manifest = tmp / "manifest.json"
self.write_jsonl(units, [self.unit()])
result = self.run_cli("validate-units", str(units), "--manifest-output", str(manifest))
self.assertEqual(result.returncode, 0, result.stderr)
report = json.loads(manifest.read_text(encoding="utf-8"))
self.assertEqual(report["total_rows"], 1)
self.assertEqual(report["error_count"], 0)
self.assertEqual(report["terminal_coverage_count"], 2)
def test_validate_patches_reports_terminal_mismatch(self) -> None:
with tempfile.TemporaryDirectory() as tmpdir:
tmp = Path(tmpdir)
units = tmp / "units.jsonl"
patches = tmp / "patches.jsonl"
self.write_jsonl(units, [self.unit(["t-1", "t-2"])])
self.write_jsonl(patches, [self.patch(["t-1"])])
result = self.run_cli("validate-patches", str(patches), "--units", str(units))
self.assertEqual(result.returncode, 1)
report = json.loads(result.stdout)
self.assertEqual(report["terminal_id_mismatch_count"], 1)
self.assertEqual(report["common_field_errors"]["terminal_ids.mismatch"], 1)
def test_compare_patches_counts_statuses_intersection_and_empty_rates(self) -> None:
with tempfile.TemporaryDirectory() as tmpdir:
tmp = Path(tmpdir)
left = tmp / "tree.jsonl"
right = tmp / "dag.jsonl"
left_rows = [
self.patch(["t-1", "t-2"], "ok"),
{
**self.patch(["t-3"], "fallback"),
"unit_id": "u-2",
"annotation": {
"episode_title_suffixes": [],
"media_suffixes": [],
"title_candidates": [],
"llm_label": None,
"notes": "empty fallback",
},
},
]
right_rows = [
self.patch(["t-2", "t-4"], "failed"),
]
right_rows[0]["errors"] = ["timeout"]
self.write_jsonl(left, left_rows)
self.write_jsonl(right, right_rows)
result = self.run_cli(
"compare-patches",
str(left),
str(right),
"--left-label",
"prefix_tree",
"--right-label",
"prefix_dag",
)
self.assertEqual(result.returncode, 0, result.stderr)
report = json.loads(result.stdout)
self.assertEqual(report["left"]["status_counts"]["ok"], 1)
self.assertEqual(report["left"]["status_counts"]["fallback"], 1)
self.assertEqual(report["right"]["status_counts"]["failed"], 1)
self.assertEqual(report["terminal_intersection_count"], 1)
self.assertEqual(report["terminal_union_count"], 4)
self.assertEqual(report["left"]["annotation_empty_rates"]["all_annotation_arrays"], 0.5)
self.assertEqual(report["right"]["text_summary"]["errors"][0]["text"], "timeout")
if __name__ == "__main__":
unittest.main()
|