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")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("ModerRAS/AniFileBERT") model = AutoModelForTokenClassification.from_pretrained("ModerRAS/AniFileBERT") - Notebooks
- Google Colab
- Kaggle
Drop multi-title synthetic templates
Browse files
tools/schema_v2_synthetic_augment/src/main.rs
CHANGED
|
@@ -697,6 +697,15 @@ fn build_numeric_record(recipe: &Recipe, title: &str, variant: usize) -> Option<
|
|
| 697 |
if classes.len() != recipe.roles.len() {
|
| 698 |
return None;
|
| 699 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 700 |
let mut builder = CharBuilder::default();
|
| 701 |
let mut previous_role = "";
|
| 702 |
for (class_name, role) in classes.iter().zip(recipe.roles.iter()) {
|
|
@@ -1412,6 +1421,24 @@ mod tests {
|
|
| 1412 |
);
|
| 1413 |
}
|
| 1414 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1415 |
#[test]
|
| 1416 |
fn path_title_season_episode_labels_are_projected() {
|
| 1417 |
let base = char_record_from_spans(
|
|
|
|
| 697 |
if classes.len() != recipe.roles.len() {
|
| 698 |
return None;
|
| 699 |
}
|
| 700 |
+
if recipe
|
| 701 |
+
.roles
|
| 702 |
+
.iter()
|
| 703 |
+
.filter(|role| role.as_str() == "TITLE")
|
| 704 |
+
.count()
|
| 705 |
+
!= 1
|
| 706 |
+
{
|
| 707 |
+
return None;
|
| 708 |
+
}
|
| 709 |
let mut builder = CharBuilder::default();
|
| 710 |
let mut previous_role = "";
|
| 711 |
for (class_name, role) in classes.iter().zip(recipe.roles.iter()) {
|
|
|
|
| 1421 |
);
|
| 1422 |
}
|
| 1423 |
|
| 1424 |
+
#[test]
|
| 1425 |
+
fn numeric_generation_drops_multi_title_templates() {
|
| 1426 |
+
let recipe = Recipe {
|
| 1427 |
+
template_id: "tpl_multi_title".to_string(),
|
| 1428 |
+
template: "TEXT SEP TEXT SEP EPISODE".to_string(),
|
| 1429 |
+
roles: vec![
|
| 1430 |
+
"TITLE".to_string(),
|
| 1431 |
+
"O".to_string(),
|
| 1432 |
+
"TITLE".to_string(),
|
| 1433 |
+
"O".to_string(),
|
| 1434 |
+
"EPISODE".to_string(),
|
| 1435 |
+
],
|
| 1436 |
+
confidence: Some("high".to_string()),
|
| 1437 |
+
_count: Some(1),
|
| 1438 |
+
};
|
| 1439 |
+
assert!(build_numeric_record(&recipe, "91 Days", 0).is_none());
|
| 1440 |
+
}
|
| 1441 |
+
|
| 1442 |
#[test]
|
| 1443 |
fn path_title_season_episode_labels_are_projected() {
|
| 1444 |
let base = char_record_from_spans(
|