Dataset tools (#2100)

* feat(dataset-tools): add dataset utilities and example script

- Introduced dataset tools for LeRobotDataset, including functions for deleting episodes, splitting datasets, adding/removing features, and merging datasets.
- Added an example script demonstrating the usage of these utilities.
- Implemented comprehensive tests for all new functionalities to ensure reliability and correctness.

* style fixes

* move example to dataset dir

* missing lisence

* fixes mostly path

* clean comments

* move tests to functions instead of class based

* - fix video editting, decode, delete frames and rencode video
- copy unchanged video and parquet files to avoid recreating the entire dataset

* Fortify tooling tests

* Fix type issue resulting from saving numpy arrays with shape 3,1,1

* added lerobot_edit_dataset

* - revert changes in examples
- remove hardcoded split names

* update comment

* fix comment
add lerobot-edit-dataset shortcut

* Apply suggestion from @Copilot

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Michel Aractingi <michel.aractingi@huggingface.co>

* style nit after copilot review

* fix: bug in dataset root when editing the dataset in place (without setting new_repo_id

* Fix bug in aggregate.py when accumelating video timestamps; add tests to fortify aggregate videos

* Added missing output repo id

* migrate delete episode to using pyav instead of decoding, writing frames to disk and encoding again.
Co-authored-by: Caroline Pascal <caroline8.pascal@gmail.com>

* added modified suffix in case repo_id is not set in delete_episode

* adding docs for dataset tools

* bump av version and add back time_base assignment

* linter

* modified push_to_hub logic in lerobot_edit_dataset

* fix(progress bar): fixing the progress bar issue in dataset tools

* chore(concatenate): removing no longer needed concatenate_datasets usage

* fix(file sizes forwarding): forwarding files and chunk sizes in metadata info when splitting and aggregating datasets

* style fix

* refactor(aggregate): Fix video indexing and timestamp bugs in dataset merging

There were three critical bugs in aggregate.py that prevented correct dataset merging:

1. Video file indices: Changed from += to = assignment to correctly reference
   merged video files

2. Video timestamps: Implemented per-source-file offset tracking to maintain
   continuous timestamps when merging split datasets (was causing non-monotonic
   timestamp warnings)

3. File rotation offsets: Store timestamp offsets after rotation decision to
   prevent out-of-bounds frame access (was causing "Invalid frame index" errors
   with small file size limits)

Changes:
- Updated update_meta_data() to apply per-source-file timestamp offsets
- Updated aggregate_videos() to track offsets correctly during file rotation
- Added get_video_duration_in_s import for duration calculation

* Improved docs for split dataset and added a check for the possible case that the split size results in zero episodes

* chore(docs): update merge documentation details

Signed-off-by: Steven Palma <imstevenpmwork@ieee.org>

---------

Co-authored-by: CarolinePascal <caroline8.pascal@gmail.com>
Co-authored-by: Jack Vial <vialjack@gmail.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>

src/lerobot/datasets/aggregate.py

@@ -39,7 +39,7 @@ from lerobot.datasets.utils import (
     write_stats,
     write_tasks,
 )
-from lerobot.datasets.video_utils import concatenate_video_files
+from lerobot.datasets.video_utils import concatenate_video_files, get_video_duration_in_s
 
 
 def validate_all_metadata(all_metadata: list[LeRobotDatasetMetadata]):
@@ -130,10 +130,34 @@ def update_meta_data(
     df["data/chunk_index"] = df["data/chunk_index"] + data_idx["chunk"]
     df["data/file_index"] = df["data/file_index"] + data_idx["file"]
     for key, video_idx in videos_idx.items():
-        df[f"videos/{key}/chunk_index"] = df[f"videos/{key}/chunk_index"] + video_idx["chunk"]
-        df[f"videos/{key}/file_index"] = df[f"videos/{key}/file_index"] + video_idx["file"]
-        df[f"videos/{key}/from_timestamp"] = df[f"videos/{key}/from_timestamp"] + video_idx["latest_duration"]
-        df[f"videos/{key}/to_timestamp"] = df[f"videos/{key}/to_timestamp"] + video_idx["latest_duration"]
+        # Store original video file indices before updating
+        orig_chunk_col = f"videos/{key}/chunk_index"
+        orig_file_col = f"videos/{key}/file_index"
+        df["_orig_chunk"] = df[orig_chunk_col].copy()
+        df["_orig_file"] = df[orig_file_col].copy()
+
+        # Update chunk and file indices to point to destination
+        df[orig_chunk_col] = video_idx["chunk"]
+        df[orig_file_col] = video_idx["file"]
+
+        # Apply per-source-file timestamp offsets
+        src_to_offset = video_idx.get("src_to_offset", {})
+        if src_to_offset:
+            # Apply offset based on original source file
+            for idx in df.index:
+                src_key = (df.at[idx, "_orig_chunk"], df.at[idx, "_orig_file"])
+                offset = src_to_offset.get(src_key, 0)
+                df.at[idx, f"videos/{key}/from_timestamp"] += offset
+                df.at[idx, f"videos/{key}/to_timestamp"] += offset
+        else:
+            # Fallback to simple offset (for backward compatibility)
+            df[f"videos/{key}/from_timestamp"] = (
+                df[f"videos/{key}/from_timestamp"] + video_idx["latest_duration"]
+            )
+            df[f"videos/{key}/to_timestamp"] = df[f"videos/{key}/to_timestamp"] + video_idx["latest_duration"]
+
+        # Clean up temporary columns
+        df = df.drop(columns=["_orig_chunk", "_orig_file"])
 
     df["dataset_from_index"] = df["dataset_from_index"] + dst_meta.info["total_frames"]
     df["dataset_to_index"] = df["dataset_to_index"] + dst_meta.info["total_frames"]
@@ -193,6 +217,9 @@ def aggregate_datasets(
         robot_type=robot_type,
         features=features,
         root=aggr_root,
+        chunks_size=chunk_size,
+        data_files_size_in_mb=data_files_size_in_mb,
+        video_files_size_in_mb=video_files_size_in_mb,
     )
 
     logging.info("Find all tasks")
@@ -236,6 +263,11 @@ def aggregate_videos(src_meta, dst_meta, videos_idx, video_files_size_in_mb, chu
     Returns:
         dict: Updated videos_idx with current chunk and file indices.
     """
+    for key in videos_idx:
+        videos_idx[key]["episode_duration"] = 0
+        # Track offset for each source (chunk, file) pair
+        videos_idx[key]["src_to_offset"] = {}
+
     for key, video_idx in videos_idx.items():
         unique_chunk_file_pairs = {
             (chunk, file)
@@ -249,6 +281,7 @@ def aggregate_videos(src_meta, dst_meta, videos_idx, video_files_size_in_mb, chu
 
         chunk_idx = video_idx["chunk"]
         file_idx = video_idx["file"]
+        current_offset = video_idx["latest_duration"]
 
         for src_chunk_idx, src_file_idx in unique_chunk_file_pairs:
             src_path = src_meta.root / DEFAULT_VIDEO_PATH.format(
@@ -263,21 +296,24 @@ def aggregate_videos(src_meta, dst_meta, videos_idx, video_files_size_in_mb, chu
                 file_index=file_idx,
             )
 
-            # If a new file is created, we don't want to increment the latest_duration
-            update_latest_duration = False
+            src_duration = get_video_duration_in_s(src_path)
 
             if not dst_path.exists():
-                # First write to this destination file
+                # Store offset before incrementing
+                videos_idx[key]["src_to_offset"][(src_chunk_idx, src_file_idx)] = current_offset
                 dst_path.parent.mkdir(parents=True, exist_ok=True)
                 shutil.copy(str(src_path), str(dst_path))
-                continue  # not accumulating further, already copied the file in place
+                videos_idx[key]["episode_duration"] += src_duration
+                current_offset += src_duration
+                continue
 
-            # Check file sizes before appending
             src_size = get_video_size_in_mb(src_path)
             dst_size = get_video_size_in_mb(dst_path)
 
             if dst_size + src_size >= video_files_size_in_mb:
-                # Rotate to a new chunk/file
+                # Rotate to a new file, this source becomes start of new destination
+                # So its offset should be 0
+                videos_idx[key]["src_to_offset"][(src_chunk_idx, src_file_idx)] = 0
                 chunk_idx, file_idx = update_chunk_file_indices(chunk_idx, file_idx, chunk_size)
                 dst_path = dst_meta.root / DEFAULT_VIDEO_PATH.format(
                     video_key=key,
@@ -286,25 +322,22 @@ def aggregate_videos(src_meta, dst_meta, videos_idx, video_files_size_in_mb, chu
                 )
                 dst_path.parent.mkdir(parents=True, exist_ok=True)
                 shutil.copy(str(src_path), str(dst_path))
+                # Reset offset for next file
+                current_offset = src_duration
             else:
-                # Get the timestamps shift for this video
-                timestamps_shift_s = dst_meta.info["total_frames"] / dst_meta.info["fps"]
-
-                # Append to existing video file
+                # Append to existing video file - use current accumulated offset
+                videos_idx[key]["src_to_offset"][(src_chunk_idx, src_file_idx)] = current_offset
                 concatenate_video_files(
                     [dst_path, src_path],
                     dst_path,
                 )
-                # Update the latest_duration when appending (shifts timestamps!)
-                update_latest_duration = not update_latest_duration
+                current_offset += src_duration
+
+            videos_idx[key]["episode_duration"] += src_duration
 
-        # Update the videos_idx with the final chunk and file indices for this key
         videos_idx[key]["chunk"] = chunk_idx
         videos_idx[key]["file"] = file_idx
 
-        if update_latest_duration:
-            videos_idx[key]["latest_duration"] += timestamps_shift_s
-
     return videos_idx
 
 
@@ -389,9 +422,6 @@ def aggregate_metadata(src_meta, dst_meta, meta_idx, data_idx, videos_idx):
             videos_idx,
         )
 
-        for k in videos_idx:
-            videos_idx[k]["latest_duration"] += videos_idx[k]["episode_duration"]
-
         meta_idx = append_or_create_parquet_file(
             df,
             src_path,
@@ -403,6 +433,10 @@ def aggregate_metadata(src_meta, dst_meta, meta_idx, data_idx, videos_idx):
             aggr_root=dst_meta.root,
         )
 
+    # Increment latest_duration by the total duration added from this source dataset
+    for k in videos_idx:
+        videos_idx[k]["latest_duration"] += videos_idx[k]["episode_duration"]
+
     return meta_idx
 
 

src/lerobot/datasets/lerobot_dataset.py

@@ -438,6 +438,9 @@ class LeRobotDatasetMetadata:
         robot_type: str | None = None,
         root: str | Path | None = None,
         use_videos: bool = True,
+        chunks_size: int | None = None,
+        data_files_size_in_mb: int | None = None,
+        video_files_size_in_mb: int | None = None,
     ) -> "LeRobotDatasetMetadata":
         """Creates metadata for a LeRobotDataset."""
         obj = cls.__new__(cls)
@@ -452,7 +455,16 @@ class LeRobotDatasetMetadata:
         obj.tasks = None
         obj.episodes = None
         obj.stats = None
-        obj.info = create_empty_dataset_info(CODEBASE_VERSION, fps, features, use_videos, robot_type)
+        obj.info = create_empty_dataset_info(
+            CODEBASE_VERSION,
+            fps,
+            features,
+            use_videos,
+            robot_type,
+            chunks_size,
+            data_files_size_in_mb,
+            video_files_size_in_mb,
+        )
         if len(obj.video_keys) > 0 and not use_videos:
             raise ValueError()
         write_json(obj.info, obj.root / INFO_PATH)

src/lerobot/datasets/utils.py

@@ -30,7 +30,7 @@ import pandas
 import pandas as pd
 import pyarrow.parquet as pq
 import torch
-from datasets import Dataset, concatenate_datasets
+from datasets import Dataset
 from datasets.table import embed_table_storage
 from huggingface_hub import DatasetCard, DatasetCardData, HfApi
 from huggingface_hub.errors import RevisionNotFoundError
@@ -44,7 +44,7 @@ from lerobot.datasets.backward_compatibility import (
     ForwardCompatibilityError,
 )
 from lerobot.utils.constants import ACTION, OBS_ENV_STATE, OBS_STR
-from lerobot.utils.utils import is_valid_numpy_dtype_string
+from lerobot.utils.utils import SuppressProgressBars, is_valid_numpy_dtype_string
 
 DEFAULT_CHUNK_SIZE = 1000  # Max number of files per chunk
 DEFAULT_DATA_FILE_SIZE_IN_MB = 100  # Max size per file
@@ -123,8 +123,9 @@ def load_nested_dataset(pq_dir: Path, features: datasets.Features | None = None)
         raise FileNotFoundError(f"Provided directory does not contain any parquet file: {pq_dir}")
 
     # TODO(rcadene): set num_proc to accelerate conversion to pyarrow
-    datasets = [Dataset.from_parquet(str(path), features=features) for path in paths]
-    return concatenate_datasets(datasets)
+    with SuppressProgressBars():
+        datasets = Dataset.from_parquet([str(path) for path in paths], features=features)
+    return datasets
 
 
 def get_parquet_num_frames(parquet_path: str | Path) -> int:

src/lerobot/datasets/video_utils.py

@@ -452,6 +452,9 @@ def concatenate_video_files(
                 template=input_stream, opaque=True
             )
 
+            # set the time base to the input stream time base (missing in the codec context)
+            stream_map[input_stream.index].time_base = input_stream.time_base
+
     # Demux + remux packets (no re-encode)
     for packet in input_container.demux():
         # Skip packets from un-mapped streams

src/lerobot/scripts/lerobot_edit_dataset.py

@@ -0,0 +1,286 @@
+#!/usr/bin/env python
+
+# Copyright 2025 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.
+
+"""
+Edit LeRobot datasets using various transformation tools.
+
+This script allows you to delete episodes, split datasets, merge datasets,
+and remove features. When new_repo_id is specified, creates a new dataset.
+
+Usage Examples:
+
+Delete episodes 0, 2, and 5 from a dataset:
+    python -m lerobot.scripts.lerobot_edit_dataset \
+        --repo_id lerobot/pusht \
+        --operation.type delete_episodes \
+        --operation.episode_indices "[0, 2, 5]"
+
+Delete episodes and save to a new dataset:
+    python -m lerobot.scripts.lerobot_edit_dataset \
+        --repo_id lerobot/pusht \
+        --new_repo_id lerobot/pusht_filtered \
+        --operation.type delete_episodes \
+        --operation.episode_indices "[0, 2, 5]"
+
+Split dataset by fractions:
+    python -m lerobot.scripts.lerobot_edit_dataset \
+        --repo_id lerobot/pusht \
+        --operation.type split \
+        --operation.splits '{"train": 0.8, "val": 0.2}'
+
+Split dataset by episode indices:
+    python -m lerobot.scripts.lerobot_edit_dataset \
+        --repo_id lerobot/pusht \
+        --operation.type split \
+        --operation.splits '{"train": [0, 1, 2, 3], "val": [4, 5]}'
+
+Split into more than two splits:
+    python -m lerobot.scripts.lerobot_edit_dataset \
+        --repo_id lerobot/pusht \
+        --operation.type split \
+        --operation.splits '{"train": 0.6, "val": 0.2, "test": 0.2}'
+
+Merge multiple datasets:
+    python -m lerobot.scripts.lerobot_edit_dataset \
+        --repo_id lerobot/pusht_merged \
+        --operation.type merge \
+        --operation.repo_ids "['lerobot/pusht_train', 'lerobot/pusht_val']"
+
+Remove camera feature:
+    python -m lerobot.scripts.lerobot_edit_dataset \
+        --repo_id lerobot/pusht \
+        --operation.type remove_feature \
+        --operation.feature_names "['observation.images.top']"
+
+Using JSON config file:
+    python -m lerobot.scripts.lerobot_edit_dataset \
+        --config_path path/to/edit_config.json
+"""
+
+import logging
+import shutil
+from dataclasses import dataclass
+from pathlib import Path
+
+from lerobot.configs import parser
+from lerobot.datasets.dataset_tools import (
+    delete_episodes,
+    merge_datasets,
+    remove_feature,
+    split_dataset,
+)
+from lerobot.datasets.lerobot_dataset import LeRobotDataset
+from lerobot.utils.constants import HF_LEROBOT_HOME
+from lerobot.utils.utils import init_logging
+
+
+@dataclass
+class DeleteEpisodesConfig:
+    type: str = "delete_episodes"
+    episode_indices: list[int] | None = None
+
+
+@dataclass
+class SplitConfig:
+    type: str = "split"
+    splits: dict[str, float | list[int]] | None = None
+
+
+@dataclass
+class MergeConfig:
+    type: str = "merge"
+    repo_ids: list[str] | None = None
+
+
+@dataclass
+class RemoveFeatureConfig:
+    type: str = "remove_feature"
+    feature_names: list[str] | None = None
+
+
+@dataclass
+class EditDatasetConfig:
+    repo_id: str
+    operation: DeleteEpisodesConfig | SplitConfig | MergeConfig | RemoveFeatureConfig
+    root: str | None = None
+    new_repo_id: str | None = None
+    push_to_hub: bool = False
+
+
+def get_output_path(repo_id: str, new_repo_id: str | None, root: Path | None) -> tuple[str, Path]:
+    if new_repo_id:
+        output_repo_id = new_repo_id
+        output_dir = root / new_repo_id if root else HF_LEROBOT_HOME / new_repo_id
+    else:
+        output_repo_id = repo_id
+        dataset_path = root / repo_id if root else HF_LEROBOT_HOME / repo_id
+        old_path = Path(str(dataset_path) + "_old")
+
+        if dataset_path.exists():
+            if old_path.exists():
+                shutil.rmtree(old_path)
+            shutil.move(str(dataset_path), str(old_path))
+
+        output_dir = dataset_path
+
+    return output_repo_id, output_dir
+
+
+def handle_delete_episodes(cfg: EditDatasetConfig) -> None:
+    if not isinstance(cfg.operation, DeleteEpisodesConfig):
+        raise ValueError("Operation config must be DeleteEpisodesConfig")
+
+    if not cfg.operation.episode_indices:
+        raise ValueError("episode_indices must be specified for delete_episodes operation")
+
+    dataset = LeRobotDataset(cfg.repo_id, root=cfg.root)
+    output_repo_id, output_dir = get_output_path(
+        cfg.repo_id, cfg.new_repo_id, Path(cfg.root) if cfg.root else None
+    )
+
+    if cfg.new_repo_id is None:
+        dataset.root = Path(str(dataset.root) + "_old")
+
+    logging.info(f"Deleting episodes {cfg.operation.episode_indices} from {cfg.repo_id}")
+    new_dataset = delete_episodes(
+        dataset,
+        episode_indices=cfg.operation.episode_indices,
+        output_dir=output_dir,
+        repo_id=output_repo_id,
+    )
+
+    logging.info(f"Dataset saved to {output_dir}")
+    logging.info(f"Episodes: {new_dataset.meta.total_episodes}, Frames: {new_dataset.meta.total_frames}")
+
+    if cfg.push_to_hub:
+        logging.info(f"Pushing to hub as {output_repo_id}")
+        LeRobotDataset(output_repo_id, root=output_dir).push_to_hub()
+
+
+def handle_split(cfg: EditDatasetConfig) -> None:
+    if not isinstance(cfg.operation, SplitConfig):
+        raise ValueError("Operation config must be SplitConfig")
+
+    if not cfg.operation.splits:
+        raise ValueError(
+            "splits dict must be specified with split names as keys and fractions/episode lists as values"
+        )
+
+    dataset = LeRobotDataset(cfg.repo_id, root=cfg.root)
+
+    logging.info(f"Splitting dataset {cfg.repo_id} with splits: {cfg.operation.splits}")
+    split_datasets = split_dataset(dataset, splits=cfg.operation.splits)
+
+    for split_name, split_ds in split_datasets.items():
+        split_repo_id = f"{cfg.repo_id}_{split_name}"
+        logging.info(
+            f"{split_name}: {split_ds.meta.total_episodes} episodes, {split_ds.meta.total_frames} frames"
+        )
+
+        if cfg.push_to_hub:
+            logging.info(f"Pushing {split_name} split to hub as {split_repo_id}")
+            LeRobotDataset(split_ds.repo_id, root=split_ds.root).push_to_hub()
+
+
+def handle_merge(cfg: EditDatasetConfig) -> None:
+    if not isinstance(cfg.operation, MergeConfig):
+        raise ValueError("Operation config must be MergeConfig")
+
+    if not cfg.operation.repo_ids:
+        raise ValueError("repo_ids must be specified for merge operation")
+
+    if not cfg.repo_id:
+        raise ValueError("repo_id must be specified as the output repository for merged dataset")
+
+    logging.info(f"Loading {len(cfg.operation.repo_ids)} datasets to merge")
+    datasets = [LeRobotDataset(repo_id, root=cfg.root) for repo_id in cfg.operation.repo_ids]
+
+    output_dir = Path(cfg.root) / cfg.repo_id if cfg.root else HF_LEROBOT_HOME / cfg.repo_id
+
+    logging.info(f"Merging datasets into {cfg.repo_id}")
+    merged_dataset = merge_datasets(
+        datasets,
+        output_repo_id=cfg.repo_id,
+        output_dir=output_dir,
+    )
+
+    logging.info(f"Merged dataset saved to {output_dir}")
+    logging.info(
+        f"Episodes: {merged_dataset.meta.total_episodes}, Frames: {merged_dataset.meta.total_frames}"
+    )
+
+    if cfg.push_to_hub:
+        logging.info(f"Pushing to hub as {cfg.repo_id}")
+        LeRobotDataset(merged_dataset.repo_id, root=output_dir).push_to_hub()
+
+
+def handle_remove_feature(cfg: EditDatasetConfig) -> None:
+    if not isinstance(cfg.operation, RemoveFeatureConfig):
+        raise ValueError("Operation config must be RemoveFeatureConfig")
+
+    if not cfg.operation.feature_names:
+        raise ValueError("feature_names must be specified for remove_feature operation")
+
+    dataset = LeRobotDataset(cfg.repo_id, root=cfg.root)
+    output_repo_id, output_dir = get_output_path(
+        cfg.repo_id, cfg.new_repo_id, Path(cfg.root) if cfg.root else None
+    )
+
+    if cfg.new_repo_id is None:
+        dataset.root = Path(str(dataset.root) + "_old")
+
+    logging.info(f"Removing features {cfg.operation.feature_names} from {cfg.repo_id}")
+    new_dataset = remove_feature(
+        dataset,
+        feature_names=cfg.operation.feature_names,
+        output_dir=output_dir,
+        repo_id=output_repo_id,
+    )
+
+    logging.info(f"Dataset saved to {output_dir}")
+    logging.info(f"Remaining features: {list(new_dataset.meta.features.keys())}")
+
+    if cfg.push_to_hub:
+        logging.info(f"Pushing to hub as {output_repo_id}")
+        LeRobotDataset(output_repo_id, root=output_dir).push_to_hub()
+
+
+@parser.wrap()
+def edit_dataset(cfg: EditDatasetConfig) -> None:
+    operation_type = cfg.operation.type
+
+    if operation_type == "delete_episodes":
+        handle_delete_episodes(cfg)
+    elif operation_type == "split":
+        handle_split(cfg)
+    elif operation_type == "merge":
+        handle_merge(cfg)
+    elif operation_type == "remove_feature":
+        handle_remove_feature(cfg)
+    else:
+        raise ValueError(
+            f"Unknown operation type: {operation_type}\n"
+            f"Available operations: delete_episodes, split, merge, remove_feature"
+        )
+
+
+def main() -> None:
+    init_logging()
+    edit_dataset()
+
+
+if __name__ == "__main__":
+    main()

src/lerobot/utils/utils.py

@@ -27,6 +27,7 @@ from statistics import mean
 
 import numpy as np
 import torch
+from datasets.utils.logging import disable_progress_bar, enable_progress_bar
 
 
 def inside_slurm():
@@ -247,6 +248,25 @@ def get_elapsed_time_in_days_hours_minutes_seconds(elapsed_time_s: float):
     return days, hours, minutes, seconds
 
 
+class SuppressProgressBars:
+    """
+    Context manager to suppress progress bars.
+
+    Example
+    --------
+    ```python
+    with SuppressProgressBars():
+        # Code that would normally show progress bars
+    ```
+    """
+
+    def __enter__(self):
+        disable_progress_bar()
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        enable_progress_bar()
+
+
 class TimerManager:
     """
     Lightweight utility to measure elapsed time.