[Chore] Bump Python version and apply formatting changes for v0.12 release (#126)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

examples/offline_inference/qwen2_5_omni/end2end.py

@@ -6,7 +6,7 @@ with the correct prompt format on Qwen2.5-Omni
 """
 
 import os
-from typing import NamedTuple, Optional
+from typing import NamedTuple
 
 import librosa
 import numpy as np
@@ -58,9 +58,9 @@ def get_text_query(question: str = None) -> QueryResult:
 
 
 def get_mixed_modalities_query(
-    video_path: Optional[str] = None,
-    image_path: Optional[str] = None,
-    audio_path: Optional[str] = None,
+    video_path: str | None = None,
+    image_path: str | None = None,
+    audio_path: str | None = None,
     num_frames: int = 16,
     sampling_rate: int = 16000,
 ) -> QueryResult:
@@ -114,7 +114,7 @@ def get_mixed_modalities_query(
 
 
 def get_use_audio_in_video_query(
-    video_path: Optional[str] = None, num_frames: int = 16, sampling_rate: int = 16000
+    video_path: str | None = None, num_frames: int = 16, sampling_rate: int = 16000
 ) -> QueryResult:
     question = "Describe the content of the video, then convert what the baby say into text."
     prompt = (
@@ -151,7 +151,7 @@ def get_use_audio_in_video_query(
     )
 
 
-def get_multi_audios_query(audio_path: Optional[str] = None, sampling_rate: int = 16000) -> QueryResult:
+def get_multi_audios_query(audio_path: str | None = None, sampling_rate: int = 16000) -> QueryResult:
     question = "Are these two audio clips the same?"
     prompt = (
         f"<|im_start|>system\n{default_system}<|im_end|>\n"
@@ -190,7 +190,7 @@ def get_multi_audios_query(audio_path: Optional[str] = None, sampling_rate: int
     )
 
 
-def get_image_query(question: str = None, image_path: Optional[str] = None) -> QueryResult:
+def get_image_query(question: str = None, image_path: str | None = None) -> QueryResult:
     if question is None:
         question = "What is the content of this image?"
     prompt = (
@@ -219,7 +219,7 @@ def get_image_query(question: str = None, image_path: Optional[str] = None) -> Q
     )
 
 
-def get_video_query(question: str = None, video_path: Optional[str] = None, num_frames: int = 16) -> QueryResult:
+def get_video_query(question: str = None, video_path: str | None = None, num_frames: int = 16) -> QueryResult:
     if question is None:
         question = "Why is this video funny?"
     prompt = (
@@ -247,7 +247,7 @@ def get_video_query(question: str = None, video_path: Optional[str] = None, num_
     )
 
 
-def get_audio_query(question: str = None, audio_path: Optional[str] = None, sampling_rate: int = 16000) -> QueryResult:
+def get_audio_query(question: str = None, audio_path: str | None = None, sampling_rate: int = 16000) -> QueryResult:
     if question is None:
         question = "What is the content of this audio?"
     prompt = (

examples/offline_inference/qwen2_5_omni/extract_prompts.py

@@ -1,9 +1,8 @@
 #!/usr/bin/env python3
 import argparse
-from typing import Optional
 
 
-def extract_prompt(line: str) -> Optional[str]:
+def extract_prompt(line: str) -> str | None:
     # Extract the content between the first '|' and the second '|'
     i = line.find("|")
     if i == -1:

examples/offline_inference/qwen3_omni/end2end.py

@@ -6,7 +6,7 @@ with the correct prompt format on Qwen3-Omni (thinker only).
 """
 
 import os
-from typing import NamedTuple, Optional
+from typing import NamedTuple
 
 import librosa
 import numpy as np
@@ -57,7 +57,7 @@ def get_text_query(question: str = None) -> QueryResult:
     )
 
 
-def get_video_query(question: str = None, video_path: Optional[str] = None, num_frames: int = 16) -> QueryResult:
+def get_video_query(question: str = None, video_path: str | None = None, num_frames: int = 16) -> QueryResult:
     if question is None:
         question = "Why is this video funny?"
     prompt = (
@@ -85,7 +85,7 @@ def get_video_query(question: str = None, video_path: Optional[str] = None, num_
     )
 
 
-def get_image_query(question: str = None, image_path: Optional[str] = None) -> QueryResult:
+def get_image_query(question: str = None, image_path: str | None = None) -> QueryResult:
     if question is None:
         question = "What is the content of this image?"
     prompt = (
@@ -114,7 +114,7 @@ def get_image_query(question: str = None, image_path: Optional[str] = None) -> Q
     )
 
 
-def get_audio_query(question: str = None, audio_path: Optional[str] = None, sampling_rate: int = 16000) -> QueryResult:
+def get_audio_query(question: str = None, audio_path: str | None = None, sampling_rate: int = 16000) -> QueryResult:
     if question is None:
         question = "What is the content of this audio?"
     prompt = (