refactor: rename types.py to schema.py to avoid stdlib conflict

whisperx/schema.py

@@ -0,0 +1,69 @@
+from typing import TypedDict, Optional, List, Tuple
+
+
+class SingleWordSegment(TypedDict):
+    """
+    A single word of a speech.
+    """
+    word: str
+    start: float
+    end: float
+    score: float
+
+class SingleCharSegment(TypedDict):
+    """
+    A single char of a speech.
+    """
+    char: str
+    start: float
+    end: float
+    score: float
+
+
+class SingleSegment(TypedDict):
+    """
+    A single segment (up to multiple sentences) of a speech.
+    """
+
+    start: float
+    end: float
+    text: str
+
+
+class SegmentData(TypedDict):
+    """
+    Temporary processing data used during alignment.
+    Contains cleaned and preprocessed data for each segment.
+    """
+    clean_char: List[str]  # Cleaned characters that exist in model dictionary
+    clean_cdx: List[int]   # Original indices of cleaned characters
+    clean_wdx: List[int]   # Indices of words containing valid characters
+    sentence_spans: List[Tuple[int, int]]  # Start and end indices of sentences
+
+
+class SingleAlignedSegment(TypedDict):
+    """
+    A single segment (up to multiple sentences) of a speech with word alignment.
+    """
+
+    start: float
+    end: float
+    text: str
+    words: List[SingleWordSegment]
+    chars: Optional[List[SingleCharSegment]]
+
+
+class TranscriptionResult(TypedDict):
+    """
+    A list of segments and word segments of a speech.
+    """
+    segments: List[SingleSegment]
+    language: str
+
+
+class AlignedTranscriptionResult(TypedDict):
+    """
+    A list of segments and word segments of a speech.
+    """
+    segments: List[SingleAlignedSegment]
+    word_segments: List[SingleWordSegment]