diff --git a/lerobot/common/datasets/image_writer.py b/lerobot/common/datasets/image_writer.py
index 6fc0ee2f..4a4e1ab0 100644
--- a/lerobot/common/datasets/image_writer.py
+++ b/lerobot/common/datasets/image_writer.py
@@ -106,7 +106,7 @@ def worker_process(queue: queue.Queue, num_threads: int):
 class AsyncImageWriter:
     """
     This class abstract away the initialisation of processes or/and threads to
-    save images on disk asynchrounously, which is critical to control a robot and record data
+    save images on disk asynchronously, which is critical to control a robot and record data
     at a high frame rate.
 
     When `num_processes=0`, it creates a threads pool of size `num_threads`.
diff --git a/lerobot/common/datasets/lerobot_dataset.py b/lerobot/common/datasets/lerobot_dataset.py
index 9d922c8a..817ab39f 100644
--- a/lerobot/common/datasets/lerobot_dataset.py
+++ b/lerobot/common/datasets/lerobot_dataset.py
@@ -932,7 +932,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
     def stop_image_writer(self) -> None:
         """
         Whenever wrapping this dataset inside a parallelized DataLoader, this needs to be called first to
-        remove the image_writer in order for the LeRobotDataset object to be pickleable and parallelized.
+        remove the image_writer in order for the LeRobotDataset object to be picklable and parallelized.
         """
         if self.image_writer is not None:
             self.image_writer.stop()
diff --git a/lerobot/common/datasets/video_utils.py b/lerobot/common/datasets/video_utils.py
index 375314e9..3a77f36e 100644
--- a/lerobot/common/datasets/video_utils.py
+++ b/lerobot/common/datasets/video_utils.py
@@ -101,7 +101,7 @@ def decode_video_frames_torchvision(
     keyframes_only = False
     torchvision.set_video_backend(backend)
     if backend == "pyav":
-        keyframes_only = True  # pyav doesnt support accuracte seek
+        keyframes_only = True  # pyav doesn't support accurate seek
 
     # set a video stream reader
     # TODO(rcadene): also load audio stream at the same time
diff --git a/lerobot/common/policies/pi0/modeling_pi0.py b/lerobot/common/policies/pi0/modeling_pi0.py
index aeb63398..1d8a5055 100644
--- a/lerobot/common/policies/pi0/modeling_pi0.py
+++ b/lerobot/common/policies/pi0/modeling_pi0.py
@@ -357,7 +357,7 @@ class PI0Policy(PreTrainedPolicy):
             if self.config.resize_imgs_with_padding is not None:
                 img = resize_with_pad(img, *self.config.resize_imgs_with_padding, pad_value=0)
 
-            # Normalize from range [0,1] to [-1,1] as expacted by siglip
+            # Normalize from range [0,1] to [-1,1] as expected by siglip
             img = img * 2.0 - 1.0
 
             bsize = img.shape[0]
diff --git a/lerobot/common/policies/pi0fast/modeling_pi0fast.py b/lerobot/common/policies/pi0fast/modeling_pi0fast.py
index 36aafce9..f19e8c83 100644
--- a/lerobot/common/policies/pi0fast/modeling_pi0fast.py
+++ b/lerobot/common/policies/pi0fast/modeling_pi0fast.py
@@ -516,7 +516,7 @@ class PI0FAST(nn.Module):
                         interpolate_like_pi=self.config.interpolate_like_pi,
                     )
 
-                # Normalize from range [0,1] to [-1,1] as expacted by siglip
+                # Normalize from range [0,1] to [-1,1] as expected by siglip
                 img = img * 2.0 - 1.0
 
                 bsize = img.shape[0]