mirror of
https://github.com/huggingface/lerobot.git
synced 2026-06-02 20:01:25 +00:00
Adds the steerable annotation pipeline (`lerobot-annotate`) that populates the `language_persistent` and `language_events` columns introduced in PR 1 directly into `data/chunk-*/file-*.parquet`. No flavor namespace, no sidecar tree. Modules produced: - Module 1 (plan_subtasks_memory): Pi0.7-style subtasks, plan (init + refresh on interjection), MEM-style memory at subtask boundaries. - Module 2 (interjections_and_speech): t=0 speech-only acknowledgement, mid-episode paired interjection + speech tool-call atom. - Module 3 (general_vqa): bbox/keypoint/count/attribute/spatial pairs at configurable cadence with one-retry JSON validation. Writer enforces: per-episode persistent identity, exact-frame event timestamps, column routing per `column_for_style`, dataset-level `tools` column with the `say` schema, drops legacy `subtask_index`. Validator runs against staged JSONL artifacts before the writer rewrites parquet. Adds `lerobot-annotate` console script, `annotations` extra (datatrove + optional vllm), `make annotation-e2e` opt-in smoke target, and `docs/source/annotation_pipeline.mdx`. Branched from PR 1 (`feat/language-columns`). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
37 lines
1.4 KiB
Python
37 lines
1.4 KiB
Python
#!/usr/bin/env python
|
|
|
|
# Copyright 2026 The HuggingFace Inc. team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
"""Steerable annotation pipeline producing ``language_persistent`` and
|
|
``language_events`` columns for LeRobot datasets.
|
|
|
|
The pipeline is decomposed into three independently runnable modules whose
|
|
outputs are staged per-episode before a final parquet rewrite:
|
|
|
|
- :mod:`.modules.plan_subtasks_memory` (Module 1) — persistent styles
|
|
- :mod:`.modules.interjections_and_speech` (Module 2) — event styles + speech
|
|
- :mod:`.modules.general_vqa` (Module 3) — event-style VQA pairs
|
|
"""
|
|
|
|
from .config import AnnotationPipelineConfig
|
|
from .validator import StagingValidator, ValidationReport
|
|
from .writer import LanguageColumnsWriter
|
|
|
|
__all__ = [
|
|
"AnnotationPipelineConfig",
|
|
"LanguageColumnsWriter",
|
|
"StagingValidator",
|
|
"ValidationReport",
|
|
]
|