Spaces:
Runtime error
Runtime error
| """Speaker chip palette, styler, and grouped-row time mapping for transcript DataFrame.""" | |
| import re | |
| import pandas as pd | |
| SPEAKER_PALETTE = [ | |
| "#FFD23F", # yellow | |
| "#FF6B6B", # coral | |
| "#5CE1E6", # cyan | |
| "#A4F47A", # lime | |
| "#FF6FC0", # magenta | |
| "#FF9F1C", # orange | |
| ] | |
| def _extract_index(label: str) -> int: | |
| """Pull a stable integer index out of a speaker label. | |
| SPEAKER_00 → 0, SPK-1 → 1, "Alice" → hash-fallback so renames keep deterministic colors | |
| only when caller passes original label; once renamed without a digit, fall back to hash. | |
| """ | |
| if not label: | |
| return 0 | |
| m = re.search(r"(\d+)", str(label)) | |
| if m: | |
| return int(m.group(1)) | |
| return abs(hash(str(label))) % len(SPEAKER_PALETTE) | |
| def color_for_speaker(label: str) -> str: | |
| return SPEAKER_PALETTE[_extract_index(label) % len(SPEAKER_PALETTE)] | |
| def render_chip(label: str) -> str: | |
| color = color_for_speaker(label) | |
| return f'<span class="brut-chip" style="background:{color}">▣ {label}</span>' | |
| def style_transcript(df: pd.DataFrame): | |
| """Return a Styler that paints the Speaker column cell background per palette.""" | |
| if df is None or df.empty or "Speaker" not in df.columns: | |
| return df | |
| def _color(value): | |
| c = color_for_speaker(value) | |
| return f"background-color: {c}; font-family: 'Archivo Black', sans-serif;" | |
| try: | |
| return df.style.applymap(_color, subset=["Speaker"]) | |
| except AttributeError: | |
| # pandas >= 2.1 deprecates applymap → use map | |
| return df.style.map(_color, subset=["Speaker"]) | |
| def grouped_row_start_seconds(merged: list, row_idx: int) -> float: | |
| """Walk merged segments, group consecutive same-speaker turns, return start seconds of group at row_idx.""" | |
| if not merged or row_idx is None or row_idx < 0: | |
| return 0.0 | |
| group_idx = -1 | |
| prev_speaker = None | |
| for seg in merged: | |
| spk = seg.get("speaker") | |
| if spk != prev_speaker: | |
| group_idx += 1 | |
| if group_idx == row_idx: | |
| return float(seg.get("start", 0.0)) | |
| prev_speaker = spk | |
| return 0.0 | |
| def build_label_map(edited_df, merged: list) -> dict: | |
| """From edited DataFrame Speaker column + original merged segments, build {orig_label → new_label}. | |
| Walks grouped segments in order, mapping each group's original speaker label to the | |
| corresponding row's edited Speaker value. | |
| """ | |
| if edited_df is None or merged is None: | |
| return {} | |
| if hasattr(edited_df, "values"): | |
| rows = edited_df.values.tolist() if isinstance(edited_df, pd.DataFrame) else edited_df | |
| if isinstance(edited_df, pd.DataFrame) and "Speaker" in edited_df.columns: | |
| new_labels = edited_df["Speaker"].tolist() | |
| else: | |
| new_labels = [r[2] for r in rows if len(r) > 2] | |
| elif isinstance(edited_df, list): | |
| new_labels = [r[2] for r in edited_df if len(r) > 2] | |
| else: | |
| return {} | |
| label_map: dict = {} | |
| group_idx = -1 | |
| prev_speaker = None | |
| for seg in merged: | |
| spk = seg.get("speaker") | |
| if spk != prev_speaker: | |
| group_idx += 1 | |
| if group_idx < len(new_labels): | |
| new_label = str(new_labels[group_idx]).strip() | |
| if new_label and new_label != spk: | |
| label_map[spk] = new_label | |
| prev_speaker = spk | |
| return label_map | |