docs: Example on PII obfuscation (#2459)

* added example on PII obfuscation Signed-off-by: Peter Staar <taa@zurich.ibm.com> * reformatting code Signed-off-by: Peter Staar <taa@zurich.ibm.com> * add in index and fix heading formatting Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add GLINER to PII Signed-off-by: Peter Staar <taa@zurich.ibm.com> * final commit Signed-off-by: Peter Staar <taa@zurich.ibm.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
2025-12-08 12:48:28 +00:00 · 2025-10-14 15:39:16 +02:00
parent cd7f7ba145
commit 3e6da2c62d
4 changed files with 472 additions and 3 deletions
--- a/docs/examples/pii_obfuscate.py
+++ b/docs/examples/pii_obfuscate.py
@@ -0,0 +1,390 @@
+# %% [markdown]
+# Detect and obfuscate PII using a Hugging Face NER model.
+#
+# What this example does
+# - Converts a PDF and saves original Markdown with embedded images.
+# - Runs a HF token-classification pipeline (NER) to detect PII-like entities.
+# - Obfuscates occurrences in TextItem and TableItem by stable, type-based IDs.
+#
+# Prerequisites
+# - Install Docling. Install Transformers: `pip install transformers`.
+# - Optional (advanced): Install GLiNER for richer PII labels:
+#     `pip install gliner`
+#     If needed for CPU-only envs:
+#     `pip install torch --extra-index-url https://download.pytorch.org/whl/cpu`
+# - Optionally, set `HF_MODEL` to a different NER/PII model.
+#
+# How to run
+# - From the repo root: `python docs/examples/pii_obfuscate.py`.
+# - To use GLiNER instead of HF pipeline:
+#     python docs/examples/pii_obfuscate.py --engine gliner
+#   or set env var `PII_ENGINE=gliner`.
+# - The script writes original and obfuscated Markdown to `scratch/`.
+#
+# Notes
+# - This is a simple demonstration. For production PII detection, consider
+#   specialized models/pipelines and thorough evaluation.
+# %%
+
+import argparse
+import logging
+import os
+import re
+from pathlib import Path
+from typing import Dict, List, Tuple
+
+from docling_core.types.doc import ImageRefMode, TableItem, TextItem
+from tabulate import tabulate
+
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.pipeline_options import PdfPipelineOptions
+from docling.document_converter import DocumentConverter, PdfFormatOption
+
+_log = logging.getLogger(__name__)
+
+IMAGE_RESOLUTION_SCALE = 2.0
+HF_MODEL = "dslim/bert-base-NER"  # Swap with another HF NER/PII model if desired, eg https://huggingface.co/urchade/gliner_multi_pii-v1 looks very promising too!
+GLINER_MODEL = "urchade/gliner_multi_pii-v1"
+
+
+def _build_simple_ner_pipeline():
+    """Create a Hugging Face token-classification pipeline for NER.
+
+    Returns a callable like: ner(text) -> List[dict]
+    """
+    try:
+        from transformers import (
+            AutoModelForTokenClassification,
+            AutoTokenizer,
+            pipeline,
+        )
+    except Exception:
+        _log.error("Transformers not installed. Please run: pip install transformers")
+        raise
+
+    tokenizer = AutoTokenizer.from_pretrained(HF_MODEL)
+    model = AutoModelForTokenClassification.from_pretrained(HF_MODEL)
+    ner = pipeline(
+        "token-classification",
+        model=model,
+        tokenizer=tokenizer,
+        aggregation_strategy="simple",  # groups subwords into complete entities
+        # Note: modern Transformers returns `start`/`end` when possible with aggregation
+    )
+    return ner
+
+
+class SimplePiiObfuscator:
+    """Tracks PII strings and replaces them with stable IDs per entity type."""
+
+    def __init__(self, ner_callable):
+        self.ner = ner_callable
+        self.entity_map: Dict[str, str] = {}
+        self.counters: Dict[str, int] = {
+            "person": 0,
+            "org": 0,
+            "location": 0,
+            "misc": 0,
+        }
+        # Map model labels to our coarse types
+        self.label_map = {
+            "PER": "person",
+            "PERSON": "person",
+            "ORG": "org",
+            "ORGANIZATION": "org",
+            "LOC": "location",
+            "LOCATION": "location",
+            "GPE": "location",
+            # Fallbacks
+            "MISC": "misc",
+            "O": "misc",
+        }
+        # Only obfuscate these by default. Adjust as needed.
+        self.allowed_types = {"person", "org", "location"}
+
+    def _next_id(self, typ: str) -> str:
+        self.counters[typ] += 1
+        return f"{typ}-{self.counters[typ]}"
+
+    def _normalize(self, s: str) -> str:
+        return re.sub(r"\s+", " ", s).strip()
+
+    def _extract_entities(self, text: str) -> List[Tuple[str, str]]:
+        """Run NER and return a list of (surface_text, type) to obfuscate."""
+        if not text:
+            return []
+        results = self.ner(text)
+        # Collect normalized items with optional span info
+        items = []
+        for r in results:
+            raw_label = r.get("entity_group") or r.get("entity") or "MISC"
+            label = self.label_map.get(raw_label, "misc")
+            if label not in self.allowed_types:
+                continue
+            start = r.get("start")
+            end = r.get("end")
+            word = self._normalize(r.get("word") or r.get("text") or "")
+            items.append({"label": label, "start": start, "end": end, "word": word})
+
+        found: List[Tuple[str, str]] = []
+        # If the pipeline provides character spans, merge consecutive/overlapping
+        # entities of the same type into a single span, then take the substring
+        # from the original text. This handles cases like subword tokenization
+        # where multiple adjacent pieces belong to the same named entity.
+        have_spans = any(i["start"] is not None and i["end"] is not None for i in items)
+        if have_spans:
+            spans = [
+                i for i in items if i["start"] is not None and i["end"] is not None
+            ]
+            # Ensure processing order by start (then end)
+            spans.sort(key=lambda x: (x["start"], x["end"]))
+
+            merged = []
+            for s in spans:
+                if not merged:
+                    merged.append(dict(s))
+                    continue
+                last = merged[-1]
+                if s["label"] == last["label"] and s["start"] <= last["end"]:
+                    # Merge identical, overlapping, or touching spans of same type
+                    last["start"] = min(last["start"], s["start"])
+                    last["end"] = max(last["end"], s["end"])
+                else:
+                    merged.append(dict(s))
+
+            for m in merged:
+                surface = self._normalize(text[m["start"] : m["end"]])
+                if surface:
+                    found.append((surface, m["label"]))
+
+            # Include any items lacking spans as-is (fallback)
+            for i in items:
+                if i["start"] is None or i["end"] is None:
+                    if i["word"]:
+                        found.append((i["word"], i["label"]))
+        else:
+            # Fallback when spans aren't provided: return normalized words
+            for i in items:
+                if i["word"]:
+                    found.append((i["word"], i["label"]))
+        return found
+
+    def obfuscate_text(self, text: str) -> str:
+        if not text:
+            return text
+
+        entities = self._extract_entities(text)
+        if not entities:
+            return text
+
+        # Deduplicate per text, keep stable global mapping
+        unique_words: Dict[str, str] = {}
+        for word, label in entities:
+            if word not in self.entity_map:
+                replacement = self._next_id(label)
+                self.entity_map[word] = replacement
+            unique_words[word] = self.entity_map[word]
+
+        # Replace longer matches first to avoid partial overlaps
+        sorted_pairs = sorted(
+            unique_words.items(), key=lambda x: len(x[0]), reverse=True
+        )
+
+        def replace_once(s: str, old: str, new: str) -> str:
+            # Use simple substring replacement; for stricter matching, use word boundaries
+            # when appropriate (e.g., names). This is a demo, keep it simple.
+            pattern = re.escape(old)
+            return re.sub(pattern, new, s)
+
+        obfuscated = text
+        for old, new in sorted_pairs:
+            obfuscated = replace_once(obfuscated, old, new)
+        return obfuscated
+
+
+def _build_gliner_model():
+    """Create a GLiNER model for PII-like entity extraction.
+
+    Returns a tuple (model, labels) where model.predict_entities(text, labels)
+    yields entities with "text" and "label" fields.
+    """
+    try:
+        from gliner import GLiNER  # type: ignore
+    except Exception:
+        _log.error(
+            "GLiNER not installed. Please run: pip install gliner torch --extra-index-url https://download.pytorch.org/whl/cpu"
+        )
+        raise
+
+    model = GLiNER.from_pretrained(GLINER_MODEL)
+    # Curated set of labels for PII detection. Adjust as needed.
+    labels = [
+        # "work",
+        "booking number",
+        "personally identifiable information",
+        "driver licence",
+        "person",
+        "full address",
+        "company",
+        # "actor",
+        # "character",
+        "email",
+        "passport number",
+        "Social Security Number",
+        "phone number",
+    ]
+    return model, labels
+
+
+class AdvancedPIIObfuscator:
+    """PII obfuscator powered by GLiNER with fine-grained labels.
+
+    - Uses GLiNER's `predict_entities(text, labels)` to detect entities.
+    - Obfuscates with stable IDs per fine-grained label, e.g. `email-1`.
+    """
+
+    def __init__(self, gliner_model, labels: List[str]):
+        self.model = gliner_model
+        self.labels = labels
+        self.entity_map: Dict[str, str] = {}
+        self.counters: Dict[str, int] = {}
+
+    def _normalize(self, s: str) -> str:
+        return re.sub(r"\s+", " ", s).strip()
+
+    def _norm_label(self, label: str) -> str:
+        return (
+            re.sub(
+                r"[^a-z0-9_]+", "_", label.lower().replace(" ", "_").replace("-", "_")
+            ).strip("_")
+            or "pii"
+        )
+
+    def _next_id(self, typ: str) -> str:
+        self.cc(typ)
+        self.counters[typ] += 1
+        return f"{typ}-{self.counters[typ]}"
+
+    def cc(self, typ: str) -> None:
+        if typ not in self.counters:
+            self.counters[typ] = 0
+
+    def _extract_entities(self, text: str) -> List[Tuple[str, str]]:
+        if not text:
+            return []
+        results = self.model.predict_entities(
+            text, self.labels
+        )  # expects dicts with text/label
+        found: List[Tuple[str, str]] = []
+        for r in results:
+            label = self._norm_label(str(r.get("label", "pii")))
+            surface = self._normalize(str(r.get("text", "")))
+            if surface:
+                found.append((surface, label))
+        return found
+
+    def obfuscate_text(self, text: str) -> str:
+        if not text:
+            return text
+        entities = self._extract_entities(text)
+        if not entities:
+            return text
+
+        unique_words: Dict[str, str] = {}
+        for word, label in entities:
+            if word not in self.entity_map:
+                replacement = self._next_id(label)
+                self.entity_map[word] = replacement
+            unique_words[word] = self.entity_map[word]
+
+        sorted_pairs = sorted(
+            unique_words.items(), key=lambda x: len(x[0]), reverse=True
+        )
+
+        def replace_once(s: str, old: str, new: str) -> str:
+            pattern = re.escape(old)
+            return re.sub(pattern, new, s)
+
+        obfuscated = text
+        for old, new in sorted_pairs:
+            obfuscated = replace_once(obfuscated, old, new)
+        return obfuscated
+
+
+def main():
+    logging.basicConfig(level=logging.INFO)
+
+    data_folder = Path(__file__).parent / "../../tests/data"
+    input_doc_path = data_folder / "pdf/2206.01062.pdf"
+    output_dir = Path("scratch")  # ensure this directory exists before saving
+
+    # Choose engine via CLI flag or env var (default: hf)
+    parser = argparse.ArgumentParser(description="PII obfuscation example")
+    parser.add_argument(
+        "--engine",
+        choices=["hf", "gliner"],
+        default=os.getenv("PII_ENGINE", "hf"),
+        help="NER engine: 'hf' (Transformers) or 'gliner' (GLiNER)",
+    )
+    args = parser.parse_args()
+
+    # Ensure output dir exists
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    # Keep and generate images so Markdown can embed them
+    pipeline_options = PdfPipelineOptions()
+    pipeline_options.images_scale = IMAGE_RESOLUTION_SCALE
+    pipeline_options.generate_page_images = True
+    pipeline_options.generate_picture_images = True
+
+    doc_converter = DocumentConverter(
+        format_options={
+            InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
+        }
+    )
+
+    conv_res = doc_converter.convert(input_doc_path)
+    conv_doc = conv_res.document
+    doc_filename = conv_res.input.file.name
+
+    # Save markdown with embedded pictures in original text
+    md_filename = output_dir / f"{doc_filename}-with-images-orig.md"
+    conv_doc.save_as_markdown(md_filename, image_mode=ImageRefMode.EMBEDDED)
+
+    # Build NER pipeline and obfuscator
+    if args.engine == "gliner":
+        _log.info("Using GLiNER-based AdvancedPIIObfuscator")
+        gliner_model, gliner_labels = _build_gliner_model()
+        obfuscator = AdvancedPIIObfuscator(gliner_model, gliner_labels)
+    else:
+        _log.info("Using HF Transformers-based SimplePiiObfuscator")
+        ner = _build_simple_ner_pipeline()
+        obfuscator = SimplePiiObfuscator(ner)
+
+    for element, _level in conv_res.document.iterate_items():
+        if isinstance(element, TextItem):
+            element.orig = element.text
+            element.text = obfuscator.obfuscate_text(element.text)
+            # print(element.orig, " => ", element.text)
+
+        elif isinstance(element, TableItem):
+            for cell in element.data.table_cells:
+                cell.text = obfuscator.obfuscate_text(cell.text)
+
+    # Save markdown with embedded pictures and obfuscated text
+    md_filename = output_dir / f"{doc_filename}-with-images-pii-obfuscated.md"
+    conv_doc.save_as_markdown(md_filename, image_mode=ImageRefMode.EMBEDDED)
+
+    # Optional: log mapping summary
+    if obfuscator.entity_map:
+        data = []
+        for key, val in obfuscator.entity_map.items():
+            data.append([key, val])
+
+        _log.info(
+            f"Obfuscated entities:\n\n{tabulate(data)}",
+        )
+
+
+if __name__ == "__main__":
+    main()
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -94,6 +94,7 @@ nav:
      - "Automatic OCR language detection with tesseract": examples/tesseract_lang_detection.py
      - "RapidOCR with custom OCR models": examples/rapidocr_with_custom_models.py
      - "Accelerator options": examples/run_with_accelerator.py
+      - "Detect and obfuscate PII": examples/pii_obfuscate.py
      - "Simple translation": examples/translate.py
      - examples/backend_csv.ipynb
      - examples/backend_xml_rag.ipynb
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -145,6 +145,7 @@ examples = [
  "langchain-milvus~=0.1",
  "langchain-text-splitters~=0.2",
  "modelscope>=1.29.0",
+  "gliner>=0.2.21",
 ]
 constraints = [
  'onnxruntime (>=1.7.0,<2.0.0) ; python_version >= "3.10"',
--- a/uv.lock
+++ b/uv.lock
@@ -1,5 +1,5 @@
 version = 1
-revision = 3
+revision = 2
 requires-python = ">=3.9, <4.0"
 resolution-markers = [
    "python_full_version >= '3.12' and platform_machine == 'arm64' and sys_platform == 'darwin'",
@@ -1181,6 +1181,7 @@ docs = [
 ]
 examples = [
    { name = "datasets" },
+    { name = "gliner" },
    { name = "langchain-huggingface" },
    { name = "langchain-milvus" },
    { name = "langchain-text-splitters" },
@@ -1267,6 +1268,7 @@ docs = [
 ]
 examples = [
    { name = "datasets", specifier = "~=2.21" },
+    { name = "gliner", specifier = ">=0.2.21" },
    { name = "langchain-huggingface", specifier = ">=0.0.3" },
    { name = "langchain-milvus", specifier = "~=0.1" },
    { name = "langchain-text-splitters", specifier = "~=0.2" },
@@ -1799,6 +1801,24 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/01/61/d4b89fec821f72385526e1b9d9a3a0385dda4a72b206d28049e2c7cd39b8/gitpython-3.1.45-py3-none-any.whl", hash = "sha256:8908cb2e02fb3b93b7eb0f2827125cb699869470432cc885f019b8fd0fccff77", size = 208168, upload-time = "2025-07-24T03:45:52.517Z" },
 ]

+[[package]]
+name = "gliner"
+version = "0.2.21"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "huggingface-hub" },
+    { name = "onnxruntime", version = "1.19.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
+    { name = "onnxruntime", version = "1.23.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10'" },
+    { name = "sentencepiece" },
+    { name = "torch" },
+    { name = "tqdm" },
+    { name = "transformers" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/6d/50/3667f92bb0ae72e2ba538ee57ecce4836770eb3b0b6c0405fbc66b1e01f2/gliner-0.2.21.tar.gz", hash = "sha256:44bc73b3e8b1a2804b333912fca729eb1fb0065f8f7b34f601bc95aa39abc749", size = 55609, upload-time = "2025-06-16T17:25:23.53Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/64/a0/120af9e76e2548d232c8e2e7eea5eb243956988cd8566422e1fc07498dc8/gliner-0.2.21-py3-none-any.whl", hash = "sha256:05f9b8f31bccd310e8d02796badb853e5c61e313af2afa252f791512d265311e", size = 65010, upload-time = "2025-06-16T17:25:22.298Z" },
+]
+
 [[package]]
 name = "griffe"
 version = "1.14.0"
@@ -5045,7 +5065,7 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/20/8a/b35a615ae6f04550d696bb179c414538b3b477999435fdd4ad75b76139e4/pybase64-1.4.2-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:a370dea7b1cee2a36a4d5445d4e09cc243816c5bc8def61f602db5a6f5438e52", size = 54320, upload-time = "2025-07-27T13:03:27.495Z" },
    { url = "https://files.pythonhosted.org/packages/d3/a9/8bd4f9bcc53689f1b457ecefed1eaa080e4949d65a62c31a38b7253d5226/pybase64-1.4.2-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:9aa4de83f02e462a6f4e066811c71d6af31b52d7484de635582d0e3ec3d6cc3e", size = 56482, upload-time = "2025-07-27T13:03:28.942Z" },
    { url = "https://files.pythonhosted.org/packages/75/e5/4a7735b54a1191f61c3f5c2952212c85c2d6b06eb5fb3671c7603395f70c/pybase64-1.4.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:83a1c2f9ed00fee8f064d548c8654a480741131f280e5750bb32475b7ec8ee38", size = 70959, upload-time = "2025-07-27T13:03:30.171Z" },
-    { url = "https://files.pythonhosted.org/packages/ca/96/7ff718f87c67f4147c181b73d0928897cefa17dc75d7abc6e37730d5908f/pybase64-1.4.2-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:fb794502b4b1ec91c4ca5d283ae71aef65e3de7721057bd9e2b3ec79f7a62d7d", size = 38230, upload-time = "2025-07-27T13:03:41.637Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/09/f3f4b11fc9beda7e8625e29fb0f549958fcbb34fea3914e1c1d95116e344/pybase64-1.4.2-cp313-cp313-android_21_x86_64.whl", hash = "sha256:9dad20bf1f3ed9e6fe566c4c9d07d9a6c04f5a280daebd2082ffb8620b0a880d", size = 40796, upload-time = "2025-07-27T13:03:36.927Z" },
    { url = "https://files.pythonhosted.org/packages/71/ab/db4dbdfccb9ca874d6ce34a0784761471885d96730de85cee3d300381529/pybase64-1.4.2-cp313-cp313-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:d377d48acf53abf4b926c2a7a24a19deb092f366a04ffd856bf4b3aa330b025d", size = 71608, upload-time = "2025-07-27T13:03:47.01Z" },
    { url = "https://files.pythonhosted.org/packages/f2/58/7f2cef1ceccc682088958448d56727369de83fa6b29148478f4d2acd107a/pybase64-1.4.2-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.whl", hash = "sha256:ab9cdb6a8176a5cb967f53e6ad60e40c83caaa1ae31c5e1b29e5c8f507f17538", size = 56413, upload-time = "2025-07-27T13:03:49.908Z" },
    { url = "https://files.pythonhosted.org/packages/08/7c/7e0af5c5728fa7e2eb082d88eca7c6bd17429be819d58518e74919d42e66/pybase64-1.4.2-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:adf0c103ad559dbfb9fe69edfd26a15c65d9c991a5ab0a25b04770f9eb0b9484", size = 59311, upload-time = "2025-07-27T13:03:51.238Z" },
@@ -5066,7 +5086,6 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/95/f0/c392c4ac8ccb7a34b28377c21faa2395313e3c676d76c382642e19a20703/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:ad59362fc267bf15498a318c9e076686e4beeb0dfe09b457fabbc2b32468b97a", size = 58103, upload-time = "2025-07-27T13:04:29.996Z" },
    { url = "https://files.pythonhosted.org/packages/32/30/00ab21316e7df8f526aa3e3dc06f74de6711d51c65b020575d0105a025b2/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:01593bd064e7dcd6c86d04e94e44acfe364049500c20ac68ca1e708fbb2ca970", size = 60779, upload-time = "2025-07-27T13:04:31.549Z" },
    { url = "https://files.pythonhosted.org/packages/a6/65/114ca81839b1805ce4a2b7d58bc16e95634734a2059991f6382fc71caf3e/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:5b81547ad8ea271c79fdf10da89a1e9313cb15edcba2a17adf8871735e9c02a0", size = 74684, upload-time = "2025-07-27T13:04:32.976Z" },
-    { url = "https://files.pythonhosted.org/packages/e1/11/b28906fc2e330b8b1ab4bc845a7bef808b8506734e90ed79c6062b095112/pybase64-1.4.2-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:cea5aaf218fd9c5c23afacfe86fd4464dfedc1a0316dd3b5b4075b068cc67df0", size = 38212, upload-time = "2025-07-27T13:04:42.729Z" },
    { url = "https://files.pythonhosted.org/packages/e4/2e/851eb51284b97354ee5dfa1309624ab90920696e91a33cd85b13d20cc5c1/pybase64-1.4.2-cp314-cp314-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:a3e54dcf0d0305ec88473c9d0009f698cabf86f88a8a10090efeff2879c421bb", size = 71674, upload-time = "2025-07-27T13:04:49.294Z" },
    { url = "https://files.pythonhosted.org/packages/a4/8e/3479266bc0e65f6cc48b3938d4a83bff045330649869d950a378f2ddece0/pybase64-1.4.2-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.whl", hash = "sha256:753da25d4fd20be7bda2746f545935773beea12d5cb5ec56ec2d2960796477b1", size = 56461, upload-time = "2025-07-27T13:04:52.37Z" },
    { url = "https://files.pythonhosted.org/packages/20/b6/f2b6cf59106dd78bae8717302be5b814cec33293504ad409a2eb752ad60c/pybase64-1.4.2-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:a78c768ce4ca550885246d14babdb8923e0f4a848dfaaeb63c38fc99e7ea4052", size = 59446, upload-time = "2025-07-27T13:04:53.967Z" },
@@ -6876,14 +6895,70 @@ version = "0.2.1"
 source = { registry = "https://pypi.org/simple" }
 sdist = { url = "https://files.pythonhosted.org/packages/15/15/2e7a025fc62d764b151ae6d0f2a92f8081755ebe8d4a64099accc6f77ba6/sentencepiece-0.2.1.tar.gz", hash = "sha256:8138cec27c2f2282f4a34d9a016e3374cd40e5c6e9cb335063db66a0a3b71fad", size = 3228515, upload-time = "2025-08-12T07:00:51.718Z" }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/af/31/5b7cccb307b485db1a2372d6d2980b0a65d067f8be5ca943a103b4acd5b3/sentencepiece-0.2.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:e10fa50bdbaa5e2445dbd387979980d391760faf0ec99a09bd7780ff37eaec44", size = 1942557, upload-time = "2025-08-12T06:59:12.379Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/41/0ac923a8e685ad290c5afc8ae55c5844977b8d75076fcc04302b9a324274/sentencepiece-0.2.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2f27ae6deea72efdb6f361750c92f6c21fd0ad087445082770cc34015213c526", size = 1325384, upload-time = "2025-08-12T06:59:14.334Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/ef/3751555d67daf9003384978f169d31c775cb5c7baf28633caaf1eb2b2b4d/sentencepiece-0.2.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:60937c959e6f44159fdd9f56fbdd302501f96114a5ba436829496d5f32d8de3f", size = 1253317, upload-time = "2025-08-12T06:59:16.247Z" },
+    { url = "https://files.pythonhosted.org/packages/46/a5/742c69b7bd144eb32b6e5fd50dbd8abbbc7a95fce2fe16e50156fa400e3b/sentencepiece-0.2.1-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d8b1d91545578852f128650b8cce4ec20f93d39b378ff554ebe66290f2dabb92", size = 1316379, upload-time = "2025-08-12T06:59:17.825Z" },
    { url = "https://files.pythonhosted.org/packages/c8/89/8deeafbba2871e8fa10f20f17447786f4ac38085925335728d360eaf4cae/sentencepiece-0.2.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:27e38eee653abc3d387862e67bc5c8b6f428cd604e688b85d29170b7e725c26c", size = 1387926, upload-time = "2025-08-12T06:59:19.395Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/ca/67fe73005f0ab617c6a970b199754e28e524b6873aa7025224fad3cda252/sentencepiece-0.2.1-cp310-cp310-win32.whl", hash = "sha256:251874d720ac7f28024a168501f3c7bb15d1802245f6e66de565f18bbb9b5eaa", size = 999550, upload-time = "2025-08-12T06:59:20.844Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/33/dc5b54042050d2dda4229c3ce1f862541c99966390b6aa20f54d520d2dc2/sentencepiece-0.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:e52144670738b4b477fade6c2a9b6af71a8d0094514c9853ac9f6fc1fcfabae7", size = 1054613, upload-time = "2025-08-12T06:59:22.255Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/19/1ea47f46ff97fe04422b78997da1a37cd632f414aae042d27a9009c5b733/sentencepiece-0.2.1-cp310-cp310-win_arm64.whl", hash = "sha256:9076430ac25dfa7147d9d05751dbc66a04bc1aaac371c07f84952979ea59f0d0", size = 1033884, upload-time = "2025-08-12T06:59:24.194Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/15/46afbab00733d81788b64be430ca1b93011bb9388527958e26cc31832de5/sentencepiece-0.2.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:6356d0986b8b8dc351b943150fcd81a1c6e6e4d439772e8584c64230e58ca987", size = 1942560, upload-time = "2025-08-12T06:59:25.82Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/79/7c01b8ef98a0567e9d84a4e7a910f8e7074fcbf398a5cd76f93f4b9316f9/sentencepiece-0.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:8f8ba89a3acb3dc1ae90f65ec1894b0b9596fdb98ab003ff38e058f898b39bc7", size = 1325385, upload-time = "2025-08-12T06:59:27.722Z" },
+    { url = "https://files.pythonhosted.org/packages/bb/88/2b41e07bd24f33dcf2f18ec3b74247aa4af3526bad8907b8727ea3caba03/sentencepiece-0.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:02593eca45440ef39247cee8c47322a34bdcc1d8ae83ad28ba5a899a2cf8d79a", size = 1253319, upload-time = "2025-08-12T06:59:29.306Z" },
+    { url = "https://files.pythonhosted.org/packages/a0/54/38a1af0c6210a3c6f95aa46d23d6640636d020fba7135cd0d9a84ada05a7/sentencepiece-0.2.1-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0a0d15781a171d188b661ae4bde1d998c303f6bd8621498c50c671bd45a4798e", size = 1316162, upload-time = "2025-08-12T06:59:30.914Z" },
    { url = "https://files.pythonhosted.org/packages/ef/66/fb191403ade791ad2c3c1e72fe8413e63781b08cfa3aa4c9dfc536d6e795/sentencepiece-0.2.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4f5a3e0d9f445ed9d66c0fec47d4b23d12cfc858b407a03c194c1b26c2ac2a63", size = 1387785, upload-time = "2025-08-12T06:59:32.491Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/2d/3bd9b08e70067b2124518b308db6a84a4f8901cc8a4317e2e4288cdd9b4d/sentencepiece-0.2.1-cp311-cp311-win32.whl", hash = "sha256:6d297a1748d429ba8534eebe5535448d78b8acc32d00a29b49acf28102eeb094", size = 999555, upload-time = "2025-08-12T06:59:34.475Z" },
+    { url = "https://files.pythonhosted.org/packages/32/b8/f709977f5fda195ae1ea24f24e7c581163b6f142b1005bc3d0bbfe4d7082/sentencepiece-0.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:82d9ead6591015f009cb1be1cb1c015d5e6f04046dbb8c9588b931e869a29728", size = 1054617, upload-time = "2025-08-12T06:59:36.461Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/40/a1fc23be23067da0f703709797b464e8a30a1c78cc8a687120cd58d4d509/sentencepiece-0.2.1-cp311-cp311-win_arm64.whl", hash = "sha256:39f8651bd10974eafb9834ce30d9bcf5b73e1fc798a7f7d2528f9820ca86e119", size = 1033877, upload-time = "2025-08-12T06:59:38.391Z" },
+    { url = "https://files.pythonhosted.org/packages/4a/be/32ce495aa1d0e0c323dcb1ba87096037358edee539cac5baf8755a6bd396/sentencepiece-0.2.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:57cae326c8727de58c85977b175af132a7138d84c764635d7e71bbee7e774133", size = 1943152, upload-time = "2025-08-12T06:59:40.048Z" },
+    { url = "https://files.pythonhosted.org/packages/88/7e/ff23008899a58678e98c6ff592bf4d368eee5a71af96d0df6b38a039dd4f/sentencepiece-0.2.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:56dd39a3c4d6493db3cdca7e8cc68c6b633f0d4195495cbadfcf5af8a22d05a6", size = 1325651, upload-time = "2025-08-12T06:59:41.536Z" },
+    { url = "https://files.pythonhosted.org/packages/19/84/42eb3ce4796777a1b5d3699dfd4dca85113e68b637f194a6c8d786f16a04/sentencepiece-0.2.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d9381351182ff9888cc80e41c632e7e274b106f450de33d67a9e8f6043da6f76", size = 1253645, upload-time = "2025-08-12T06:59:42.903Z" },
+    { url = "https://files.pythonhosted.org/packages/89/fa/d3d5ebcba3cb9e6d3775a096251860c41a6bc53a1b9461151df83fe93255/sentencepiece-0.2.1-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:99f955df238021bf11f0fc37cdb54fd5e5b5f7fd30ecc3d93fb48b6815437167", size = 1316273, upload-time = "2025-08-12T06:59:44.476Z" },
    { url = "https://files.pythonhosted.org/packages/04/88/14f2f4a2b922d8b39be45bf63d79e6cd3a9b2f248b2fcb98a69b12af12f5/sentencepiece-0.2.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0cdfecef430d985f1c2bcbfff3defd1d95dae876fbd0173376012d2d7d24044b", size = 1387881, upload-time = "2025-08-12T06:59:46.09Z" },
+    { url = "https://files.pythonhosted.org/packages/fd/b8/903e5ccb77b4ef140605d5d71b4f9e0ad95d456d6184688073ed11712809/sentencepiece-0.2.1-cp312-cp312-win32.whl", hash = "sha256:a483fd29a34c3e34c39ac5556b0a90942bec253d260235729e50976f5dba1068", size = 999540, upload-time = "2025-08-12T06:59:48.023Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/81/92df5673c067148c2545b1bfe49adfd775bcc3a169a047f5a0e6575ddaca/sentencepiece-0.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:4cdc7c36234fda305e85c32949c5211faaf8dd886096c7cea289ddc12a2d02de", size = 1054671, upload-time = "2025-08-12T06:59:49.895Z" },
+    { url = "https://files.pythonhosted.org/packages/fe/02/c5e3bc518655d714622bec87d83db9cdba1cd0619a4a04e2109751c4f47f/sentencepiece-0.2.1-cp312-cp312-win_arm64.whl", hash = "sha256:daeb5e9e9fcad012324807856113708614d534f596d5008638eb9b40112cd9e4", size = 1033923, upload-time = "2025-08-12T06:59:51.952Z" },
+    { url = "https://files.pythonhosted.org/packages/ba/4a/85fbe1706d4d04a7e826b53f327c4b80f849cf1c7b7c5e31a20a97d8f28b/sentencepiece-0.2.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:dcd8161eee7b41aae57ded06272905dbd680a0a04b91edd0f64790c796b2f706", size = 1943150, upload-time = "2025-08-12T06:59:53.588Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/83/4cfb393e287509fc2155480b9d184706ef8d9fa8cbf5505d02a5792bf220/sentencepiece-0.2.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:c6c8f42949f419ff8c7e9960dbadcfbc982d7b5efc2f6748210d3dd53a7de062", size = 1325651, upload-time = "2025-08-12T06:59:55.073Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/de/5a007fb53b1ab0aafc69d11a5a3dd72a289d5a3e78dcf2c3a3d9b14ffe93/sentencepiece-0.2.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:097f3394e99456e9e4efba1737c3749d7e23563dd1588ce71a3d007f25475fff", size = 1253641, upload-time = "2025-08-12T06:59:56.562Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/d2/f552be5928105588f4f4d66ee37dd4c61460d8097e62d0e2e0eec41bc61d/sentencepiece-0.2.1-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d7b670879c370d350557edabadbad1f6561a9e6968126e6debca4029e5547820", size = 1316271, upload-time = "2025-08-12T06:59:58.109Z" },
    { url = "https://files.pythonhosted.org/packages/96/df/0cfe748ace5485be740fed9476dee7877f109da32ed0d280312c94ec259f/sentencepiece-0.2.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c7f0fd2f2693309e6628aeeb2e2faf6edd221134dfccac3308ca0de01f8dab47", size = 1387882, upload-time = "2025-08-12T07:00:00.701Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/dd/f7774d42a881ced8e1739f393ab1e82ece39fc9abd4779e28050c2e975b5/sentencepiece-0.2.1-cp313-cp313-win32.whl", hash = "sha256:92b3816aa2339355fda2c8c4e021a5de92180b00aaccaf5e2808972e77a4b22f", size = 999541, upload-time = "2025-08-12T07:00:02.709Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/e9/932b9eae6fd7019548321eee1ab8d5e3b3d1294df9d9a0c9ac517c7b636d/sentencepiece-0.2.1-cp313-cp313-win_amd64.whl", hash = "sha256:10ed3dab2044c47f7a2e7b4969b0c430420cdd45735d78c8f853191fa0e3148b", size = 1054669, upload-time = "2025-08-12T07:00:04.915Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/3a/76488a00ea7d6931689cda28726a1447d66bf1a4837943489314593d5596/sentencepiece-0.2.1-cp313-cp313-win_arm64.whl", hash = "sha256:ac650534e2251083c5f75dde4ff28896ce7c8904133dc8fef42780f4d5588fcd", size = 1033922, upload-time = "2025-08-12T07:00:06.496Z" },
+    { url = "https://files.pythonhosted.org/packages/4a/b6/08fe2ce819e02ccb0296f4843e3f195764ce9829cbda61b7513f29b95718/sentencepiece-0.2.1-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:8dd4b477a7b069648d19363aad0cab9bad2f4e83b2d179be668efa672500dc94", size = 1946052, upload-time = "2025-08-12T07:00:08.136Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/d9/1ea0e740591ff4c6fc2b6eb1d7510d02f3fb885093f19b2f3abd1363b402/sentencepiece-0.2.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0c0f672da370cc490e4c59d89e12289778310a0e71d176c541e4834759e1ae07", size = 1327408, upload-time = "2025-08-12T07:00:09.572Z" },
+    { url = "https://files.pythonhosted.org/packages/99/7e/1fb26e8a21613f6200e1ab88824d5d203714162cf2883248b517deb500b7/sentencepiece-0.2.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:ad8493bea8432dae8d6830365352350f3b4144415a1d09c4c8cb8d30cf3b6c3c", size = 1254857, upload-time = "2025-08-12T07:00:11.021Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/85/c72fd1f3c7a6010544d6ae07f8ddb38b5e2a7e33bd4318f87266c0bbafbf/sentencepiece-0.2.1-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b81a24733726e3678d2db63619acc5a8dccd074f7aa7a54ecd5ca33ca6d2d596", size = 1315722, upload-time = "2025-08-12T07:00:12.989Z" },
    { url = "https://files.pythonhosted.org/packages/4a/e8/661e5bd82a8aa641fd6c1020bd0e890ef73230a2b7215ddf9c8cd8e941c2/sentencepiece-0.2.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0a81799d0a68d618e89063fb423c3001a034c893069135ffe51fee439ae474d6", size = 1387452, upload-time = "2025-08-12T07:00:15.088Z" },
+    { url = "https://files.pythonhosted.org/packages/99/5e/ae66c361023a470afcbc1fbb8da722c72ea678a2fcd9a18f1a12598c7501/sentencepiece-0.2.1-cp313-cp313t-win32.whl", hash = "sha256:89a3ea015517c42c0341d0d962f3e6aaf2cf10d71b1932d475c44ba48d00aa2b", size = 1002501, upload-time = "2025-08-12T07:00:16.966Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/03/d332828c4ff764e16c1b56c2c8f9a33488bbe796b53fb6b9c4205ddbf167/sentencepiece-0.2.1-cp313-cp313t-win_amd64.whl", hash = "sha256:33f068c9382dc2e7c228eedfd8163b52baa86bb92f50d0488bf2b7da7032e484", size = 1057555, upload-time = "2025-08-12T07:00:18.573Z" },
+    { url = "https://files.pythonhosted.org/packages/88/14/5aee0bf0864df9bd82bd59e7711362908e4935e3f9cdc1f57246b5d5c9b9/sentencepiece-0.2.1-cp313-cp313t-win_arm64.whl", hash = "sha256:b3616ad246f360e52c85781e47682d31abfb6554c779e42b65333d4b5f44ecc0", size = 1036042, upload-time = "2025-08-12T07:00:20.209Z" },
+    { url = "https://files.pythonhosted.org/packages/24/9c/89eb8b2052f720a612478baf11c8227dcf1dc28cd4ea4c0c19506b5af2a2/sentencepiece-0.2.1-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:5d0350b686c320068702116276cfb26c066dc7e65cfef173980b11bb4d606719", size = 1943147, upload-time = "2025-08-12T07:00:21.809Z" },
+    { url = "https://files.pythonhosted.org/packages/82/0b/a1432bc87f97c2ace36386ca23e8bd3b91fb40581b5e6148d24b24186419/sentencepiece-0.2.1-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:c7f54a31cde6fa5cb030370566f68152a742f433f8d2be458463d06c208aef33", size = 1325624, upload-time = "2025-08-12T07:00:23.289Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/99/bbe054ebb5a5039457c590e0a4156ed073fb0fe9ce4f7523404dd5b37463/sentencepiece-0.2.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c83b85ab2d6576607f31df77ff86f28182be4a8de6d175d2c33ca609925f5da1", size = 1253670, upload-time = "2025-08-12T07:00:24.69Z" },
+    { url = "https://files.pythonhosted.org/packages/19/ad/d5c7075f701bd97971d7c2ac2904f227566f51ef0838dfbdfdccb58cd212/sentencepiece-0.2.1-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1855f57db07b51fb51ed6c9c452f570624d2b169b36f0f79ef71a6e6c618cd8b", size = 1316247, upload-time = "2025-08-12T07:00:26.435Z" },
    { url = "https://files.pythonhosted.org/packages/fb/03/35fbe5f3d9a7435eebd0b473e09584bd3cc354ce118b960445b060d33781/sentencepiece-0.2.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:01e6912125cb45d3792f530a4d38f8e21bf884d6b4d4ade1b2de5cf7a8d2a52b", size = 1387894, upload-time = "2025-08-12T07:00:28.339Z" },
+    { url = "https://files.pythonhosted.org/packages/dc/aa/956ef729aafb6c8f9c443104c9636489093bb5c61d6b90fc27aa1a865574/sentencepiece-0.2.1-cp314-cp314-win32.whl", hash = "sha256:c415c9de1447e0a74ae3fdb2e52f967cb544113a3a5ce3a194df185cbc1f962f", size = 1096698, upload-time = "2025-08-12T07:00:29.764Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/cb/fe400d8836952cc535c81a0ce47dc6875160e5fedb71d2d9ff0e9894c2a6/sentencepiece-0.2.1-cp314-cp314-win_amd64.whl", hash = "sha256:881b2e44b14fc19feade3cbed314be37de639fc415375cefaa5bc81a4be137fd", size = 1155115, upload-time = "2025-08-12T07:00:32.865Z" },
+    { url = "https://files.pythonhosted.org/packages/32/89/047921cf70f36c7b6b6390876b2399b3633ab73b8d0cb857e5a964238941/sentencepiece-0.2.1-cp314-cp314-win_arm64.whl", hash = "sha256:2005242a16d2dc3ac5fe18aa7667549134d37854823df4c4db244752453b78a8", size = 1133890, upload-time = "2025-08-12T07:00:34.763Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/11/5b414b9fae6255b5fb1e22e2ed3dc3a72d3a694e5703910e640ac78346bb/sentencepiece-0.2.1-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:a19adcec27c524cb7069a1c741060add95f942d1cbf7ad0d104dffa0a7d28a2b", size = 1946081, upload-time = "2025-08-12T07:00:36.97Z" },
+    { url = "https://files.pythonhosted.org/packages/77/eb/7a5682bb25824db8545f8e5662e7f3e32d72a508fdce086029d89695106b/sentencepiece-0.2.1-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:e37e4b4c4a11662b5db521def4e44d4d30ae69a1743241412a93ae40fdcab4bb", size = 1327406, upload-time = "2025-08-12T07:00:38.669Z" },
+    { url = "https://files.pythonhosted.org/packages/03/b0/811dae8fb9f2784e138785d481469788f2e0d0c109c5737372454415f55f/sentencepiece-0.2.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:477c81505db072b3ab627e7eab972ea1025331bd3a92bacbf798df2b75ea86ec", size = 1254846, upload-time = "2025-08-12T07:00:40.611Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/23/195b2e7ec85ebb6a547969f60b723c7aca5a75800ece6cc3f41da872d14e/sentencepiece-0.2.1-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:010f025a544ef770bb395091d57cb94deb9652d8972e0d09f71d85d5a0816c8c", size = 1315721, upload-time = "2025-08-12T07:00:42.914Z" },
    { url = "https://files.pythonhosted.org/packages/7e/aa/553dbe4178b5f23eb28e59393dddd64186178b56b81d9b8d5c3ff1c28395/sentencepiece-0.2.1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:733e59ff1794d26db706cd41fc2d7ca5f6c64a820709cb801dc0ea31780d64ab", size = 1387458, upload-time = "2025-08-12T07:00:44.56Z" },
+    { url = "https://files.pythonhosted.org/packages/66/7c/08ff0012507297a4dd74a5420fdc0eb9e3e80f4e88cab1538d7f28db303d/sentencepiece-0.2.1-cp314-cp314t-win32.whl", hash = "sha256:d3233770f78e637dc8b1fda2cd7c3b99ec77e7505041934188a4e7fe751de3b0", size = 1099765, upload-time = "2025-08-12T07:00:46.058Z" },
+    { url = "https://files.pythonhosted.org/packages/91/d5/2a69e1ce15881beb9ddfc7e3f998322f5cedcd5e4d244cb74dade9441663/sentencepiece-0.2.1-cp314-cp314t-win_amd64.whl", hash = "sha256:5e4366c97b68218fd30ea72d70c525e6e78a6c0a88650f57ac4c43c63b234a9d", size = 1157807, upload-time = "2025-08-12T07:00:47.673Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/16/54f611fcfc2d1c46cbe3ec4169780b2cfa7cf63708ef2b71611136db7513/sentencepiece-0.2.1-cp314-cp314t-win_arm64.whl", hash = "sha256:105e36e75cbac1292642045458e8da677b2342dcd33df503e640f0b457cb6751", size = 1136264, upload-time = "2025-08-12T07:00:49.485Z" },
+    { url = "https://files.pythonhosted.org/packages/98/df/76390cc0bb812687f5fa7574b555354197b8e8fdb9aaf5c9c28ae58e148b/sentencepiece-0.2.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:afefe50a0cdcb4f2fd9733cb52001a2c164181ee2d82c32d38f5b1b326a8528c", size = 1942582, upload-time = "2025-08-12T06:58:59.807Z" },
+    { url = "https://files.pythonhosted.org/packages/24/51/ff7ff849a7f139535d0309fe2a351379459bac5332127eb9a3a955ef2847/sentencepiece-0.2.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:891ade6503dd93d418c03993f7d6a8aa20260c422cefff5096b9068185e67642", size = 1325367, upload-time = "2025-08-12T06:59:01.677Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/29/bca460c34ebc79a1f3706d0eebceecd1187b2b9b93bc211f177e3b520eb0/sentencepiece-0.2.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:814978ac05130dd5812b4b03215c766bc6abaef13e7bd72bc534e4d1e12e9a4c", size = 1253366, upload-time = "2025-08-12T06:59:03.252Z" },
+    { url = "https://files.pythonhosted.org/packages/5e/98/f279374c1e86d2a735c7d063d5b800608fc7b8370319121a9fc501cf9091/sentencepiece-0.2.1-cp39-cp39-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:017f97b274d4b0baa84b2dc743bf4517be81156f413bb24f12aacacde378e5ab", size = 1316437, upload-time = "2025-08-12T06:59:04.832Z" },
    { url = "https://files.pythonhosted.org/packages/32/d7/efd7e172875f1329d8ae43e55f853776e332542ecb881a11a6b67d49c98c/sentencepiece-0.2.1-cp39-cp39-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:22c4ebcb3c6ab1496ab1c37c79ef7bb563b8726f29548c30773b7a4cb152df1a", size = 1387621, upload-time = "2025-08-12T06:59:06.445Z" },
+    { url = "https://files.pythonhosted.org/packages/e0/a5/cc46d5308e1056d756b20211f039f609c86d3073aa66088cd5af57a652fa/sentencepiece-0.2.1-cp39-cp39-win32.whl", hash = "sha256:caa4e560c72c151da80036aecc2159e51a7fd8ae9efebefd96860460ce6bd025", size = 999563, upload-time = "2025-08-12T06:59:07.833Z" },
+    { url = "https://files.pythonhosted.org/packages/87/06/94bc50dc6b113bbf5f4ba7bfe85cfa7d62c679f9fb68f658d48f3ea556cf/sentencepiece-0.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:2af5a1fb05013332ad94343b8b5f3973e006a2dde2dfba55a819549e054e2f0f", size = 1054663, upload-time = "2025-08-12T06:59:09.234Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/21/55267fcdc1a99612248c299c12d8f7c51d6e5ae992f32694d17adcf13fda/sentencepiece-0.2.1-cp39-cp39-win_arm64.whl", hash = "sha256:3d165fbb9bf8fba35f1946ba2617c3f9995679f07438325f07c026d53f33e746", size = 1033914, upload-time = "2025-08-12T06:59:10.705Z" },
 ]

 [[package]]
@@ -7142,7 +7217,9 @@ dependencies = [
 sdist = { url = "https://files.pythonhosted.org/packages/e1/41/9b873a8c055582859b239be17902a85339bec6a30ad162f98c9b0288a2cc/soundfile-0.13.1.tar.gz", hash = "sha256:b2c68dab1e30297317080a5b43df57e302584c49e2942defdde0acccc53f0e5b", size = 46156, upload-time = "2025-01-25T09:17:04.831Z" }
 wheels = [
    { url = "https://files.pythonhosted.org/packages/64/28/e2a36573ccbcf3d57c00626a21fe51989380636e821b341d36ccca0c1c3a/soundfile-0.13.1-py2.py3-none-any.whl", hash = "sha256:a23c717560da2cf4c7b5ae1142514e0fd82d6bbd9dfc93a50423447142f2c445", size = 25751, upload-time = "2025-01-25T09:16:44.235Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/ab/73e97a5b3cc46bba7ff8650a1504348fa1863a6f9d57d7001c6b67c5f20e/soundfile-0.13.1-py2.py3-none-macosx_10_9_x86_64.whl", hash = "sha256:82dc664d19831933fe59adad199bf3945ad06d84bc111a5b4c0d3089a5b9ec33", size = 1142250, upload-time = "2025-01-25T09:16:47.583Z" },
    { url = "https://files.pythonhosted.org/packages/a0/e5/58fd1a8d7b26fc113af244f966ee3aecf03cb9293cb935daaddc1e455e18/soundfile-0.13.1-py2.py3-none-macosx_11_0_arm64.whl", hash = "sha256:743f12c12c4054921e15736c6be09ac26b3b3d603aef6fd69f9dde68748f2593", size = 1101406, upload-time = "2025-01-25T09:16:49.662Z" },
+    { url = "https://files.pythonhosted.org/packages/58/ae/c0e4a53d77cf6e9a04179535766b3321b0b9ced5f70522e4caf9329f0046/soundfile-0.13.1-py2.py3-none-manylinux_2_28_aarch64.whl", hash = "sha256:9c9e855f5a4d06ce4213f31918653ab7de0c5a8d8107cd2427e44b42df547deb", size = 1235729, upload-time = "2025-01-25T09:16:53.018Z" },
    { url = "https://files.pythonhosted.org/packages/57/5e/70bdd9579b35003a489fc850b5047beeda26328053ebadc1fb60f320f7db/soundfile-0.13.1-py2.py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:03267c4e493315294834a0870f31dbb3b28a95561b80b134f0bd3cf2d5f0e618", size = 1313646, upload-time = "2025-01-25T09:16:54.872Z" },
 ]