karaoke-gen 0.75.54__py3-none-any.whl

lyrics_transcriber/frontend/src/types.ts

@@ -0,0 +1,199 @@
+export interface Word {
+    id: string
+    text: string
+    start_time: number | null
+    end_time: number | null
+    confidence?: number
+    created_during_correction?: boolean
+}
+
+export interface LyricsSegment {
+    id: string
+    text: string
+    words: Word[]
+    start_time: number | null
+    end_time: number | null
+}
+
+export interface WordCorrection {
+    id?: string
+    handler: string
+    original_word: string
+    corrected_word: string
+    segment_id?: string
+    word_id: string
+    corrected_word_id: string | null
+    source: string
+    confidence: number
+    reason: string
+    alternatives: Record<string, number>
+    is_deletion: boolean
+    split_index?: number | null
+    split_total?: number | null
+    reference_positions?: Record<string, number>
+    length: number
+}
+
+export interface PhraseScore {
+    phrase_type: string
+    natural_break_score: number
+    length_score: number
+    total_score: number
+}
+
+export interface AnchorSequence {
+    id: string
+    transcribed_word_ids: string[]
+    transcription_position: number
+    reference_positions: Record<string, number>
+    reference_word_ids: {
+        [source: string]: string[]
+    }
+    confidence: number
+    phrase_score?: PhraseScore
+    total_score?: number
+}
+
+export interface GapSequence {
+    id: string
+    transcribed_word_ids: string[]
+    transcription_position: number
+    preceding_anchor_id: string | null
+    following_anchor_id: string | null
+    reference_word_ids: {
+        [source: string]: string[]
+    }
+}
+
+export interface ReferenceSource {
+    segments: LyricsSegment[]
+    metadata: {
+        source: string
+        track_name: string | null
+        artist_names: string | null
+        album_name: string | null
+        duration_ms: number | null
+        explicit: boolean | null
+        language: string | null
+        is_synced: boolean
+        lyrics_provider: string
+        lyrics_provider_id: string
+        provider_metadata: Record<string, unknown>
+    }
+    source: string
+}
+
+export interface CorrectionStep {
+    handler_name: string
+    affected_word_ids: string[]
+    affected_segment_ids: string[]
+    corrections: WordCorrection[]
+    segments_before: LyricsSegment[]
+    segments_after: LyricsSegment[]
+    created_word_ids: string[]
+    deleted_word_ids: string[]
+}
+
+export interface CorrectionHandler {
+    id: string
+    name: string
+    description: string
+    enabled: boolean
+}
+
+export interface CorrectionData {
+    original_segments: LyricsSegment[]
+    reference_lyrics: Record<string, ReferenceSource>
+    anchor_sequences: AnchorSequence[]
+    gap_sequences: GapSequence[]
+    resized_segments: LyricsSegment[]
+    corrections_made: number
+    confidence: number
+    corrections: WordCorrection[]
+    corrected_segments: LyricsSegment[]
+    metadata: {
+        anchor_sequences_count: number
+        gap_sequences_count: number
+        total_words: number
+        correction_ratio: number
+        audio_filepath?: string
+        audio_hash?: string
+        available_handlers?: CorrectionHandler[]
+        enabled_handlers?: string[]
+    }
+    correction_steps: CorrectionStep[]
+    word_id_map: Record<string, string>
+    segment_id_map: Record<string, string>
+}
+
+export interface HighlightInfo {
+    type: 'single' | 'gap' | 'anchor' | 'correction'
+    sequence?: AnchorSequence | GapSequence
+    transcribed_words: Word[]
+    reference_words?: {
+        [source: string]: Word[]
+    }
+    correction?: WordCorrection
+}
+
+export type InteractionMode = 'highlight' | 'edit' | 'delete_word'
+
+// Correction Annotation Types
+export type CorrectionAnnotationType = 
+    | 'PUNCTUATION_ONLY'
+    | 'SOUND_ALIKE'
+    | 'BACKGROUND_VOCALS'
+    | 'EXTRA_WORDS'
+    | 'REPEATED_SECTION'
+    | 'COMPLEX_MULTI_ERROR'
+    | 'AMBIGUOUS'
+    | 'NO_ERROR'
+    | 'MANUAL_EDIT'
+
+export type CorrectionAction = 
+    | 'NO_ACTION'
+    | 'REPLACE'
+    | 'DELETE'
+    | 'INSERT'
+    | 'MERGE'
+    | 'SPLIT'
+    | 'FLAG'
+
+export interface CorrectionAnnotation {
+    annotation_id: string
+    audio_hash: string
+    gap_id: string | null
+    annotation_type: CorrectionAnnotationType
+    action_taken: CorrectionAction
+    original_text: string
+    corrected_text: string
+    confidence: number  // 1-5 scale
+    reasoning: string
+    word_ids_affected: string[]
+    agentic_proposal: {
+        action: string
+        replacement_text?: string
+        confidence: number
+        reason: string
+        gap_category?: string
+    } | null
+    agentic_category: string | null
+    agentic_agreed: boolean
+    reference_sources_consulted: string[]
+    artist: string
+    title: string
+    session_id: string
+    timestamp?: string
+}
+
+export interface CorrectionActionEvent {
+    type: 'revert' | 'edit' | 'accept' | 'reject'
+    correctionId: string
+    wordId: string
+}
+
+export interface GapCategoryMetric {
+    category: string
+    count: number
+    avgConfidence: number
+}

lyrics_transcriber/frontend/src/validation.ts

@@ -0,0 +1,132 @@
+import { z } from 'zod'
+
+// Define schemas that match our TypeScript interfaces
+const WordSchema = z.object({
+    id: z.string(),
+    text: z.string(),
+    start_time: z.number().nullable(),
+    end_time: z.number().nullable(),
+    confidence: z.number().optional(),
+    created_during_correction: z.boolean().optional()
+})
+
+const LyricsSegmentSchema = z.object({
+    id: z.string(),
+    text: z.string(),
+    words: z.array(WordSchema),
+    start_time: z.number().nullable(),
+    end_time: z.number().nullable()
+})
+
+const WordCorrectionSchema = z.object({
+    id: z.string().optional(),
+    handler: z.string(),
+    original_word: z.string(),
+    corrected_word: z.string(),
+    segment_id: z.string().optional(),
+    word_id: z.string(),
+    corrected_word_id: z.string().nullable(),
+    source: z.string(),
+    confidence: z.number(),
+    reason: z.string(),
+    alternatives: z.record(z.number()),
+    is_deletion: z.boolean(),
+    split_index: z.number().nullable().optional(),
+    split_total: z.number().nullable().optional(),
+    reference_positions: z.record(z.number()).optional(),
+    length: z.number()
+})
+
+const ReferenceSourceSchema = z.object({
+    segments: z.array(LyricsSegmentSchema),
+    metadata: z.object({
+        source: z.string(),
+        track_name: z.string().nullable(),
+        artist_names: z.string().nullable(),
+        album_name: z.string().nullable(),
+        duration_ms: z.number().nullable(),
+        explicit: z.boolean().nullable(),
+        language: z.string().nullable(),
+        is_synced: z.boolean(),
+        lyrics_provider: z.string(),
+        lyrics_provider_id: z.string(),
+        provider_metadata: z.record(z.unknown())
+    }),
+    source: z.string()
+})
+
+const PhraseScoreSchema = z.object({
+    phrase_type: z.string(),
+    natural_break_score: z.number(),
+    length_score: z.number(),
+    total_score: z.number()
+})
+
+const AnchorSequenceSchema = z.object({
+    id: z.string(),
+    transcribed_word_ids: z.array(z.string()),
+    transcription_position: z.number(),
+    reference_positions: z.record(z.number()),
+    reference_word_ids: z.record(z.array(z.string())),
+    confidence: z.number(),
+    phrase_score: PhraseScoreSchema.optional(),
+    total_score: z.number().optional()
+})
+
+const GapSequenceSchema = z.object({
+    id: z.string(),
+    transcribed_word_ids: z.array(z.string()),
+    transcription_position: z.number(),
+    preceding_anchor_id: z.string().nullable(),
+    following_anchor_id: z.string().nullable(),
+    reference_word_ids: z.record(z.array(z.string()))
+})
+
+const CorrectionStepSchema = z.object({
+    handler_name: z.string(),
+    affected_word_ids: z.array(z.string()),
+    affected_segment_ids: z.array(z.string()),
+    corrections: z.array(WordCorrectionSchema),
+    segments_before: z.array(LyricsSegmentSchema),
+    segments_after: z.array(LyricsSegmentSchema),
+    created_word_ids: z.array(z.string()),
+    deleted_word_ids: z.array(z.string())
+})
+
+// Add new schema for correction handlers
+const CorrectionHandlerSchema = z.object({
+    id: z.string(),
+    name: z.string(),
+    description: z.string(),
+    enabled: z.boolean()
+})
+
+// Update CorrectionDataSchema to include handler information
+const CorrectionDataSchema = z.object({
+    original_segments: z.array(LyricsSegmentSchema),
+    reference_lyrics: z.record(ReferenceSourceSchema),
+    anchor_sequences: z.array(AnchorSequenceSchema),
+    gap_sequences: z.array(GapSequenceSchema),
+    resized_segments: z.array(LyricsSegmentSchema),
+    corrections_made: z.number(),
+    confidence: z.number(),
+    corrections: z.array(WordCorrectionSchema),
+    corrected_segments: z.array(LyricsSegmentSchema),
+    metadata: z.object({
+        anchor_sequences_count: z.number(),
+        gap_sequences_count: z.number(),
+        total_words: z.number(),
+        correction_ratio: z.number(),
+        audio_filepath: z.string().optional(),
+        audio_hash: z.string().optional(),
+        available_handlers: z.array(CorrectionHandlerSchema).optional(),
+        enabled_handlers: z.array(z.string()).optional()
+    }),
+    correction_steps: z.array(CorrectionStepSchema),
+    word_id_map: z.record(z.string()),
+    segment_id_map: z.record(z.string())
+})
+
+export function validateCorrectionData(data: unknown) {
+    return CorrectionDataSchema.parse(data)
+} 

lyrics_transcriber/frontend/src/vite-env.d.ts

@@ -0,0 +1 @@
+/// <reference types="vite/client" />

lyrics_transcriber/frontend/tsconfig.app.json

@@ -0,0 +1,26 @@
+{
+  "compilerOptions": {
+    "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.app.tsbuildinfo",
+    "target": "ES2020",
+    "useDefineForClassFields": true,
+    "lib": ["ES2020", "DOM", "DOM.Iterable"],
+    "module": "ESNext",
+    "skipLibCheck": true,
+
+    /* Bundler mode */
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "isolatedModules": true,
+    "moduleDetection": "force",
+    "noEmit": true,
+    "jsx": "react-jsx",
+
+    /* Linting */
+    "strict": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "noFallthroughCasesInSwitch": true,
+    "noUncheckedSideEffectImports": true
+  },
+  "include": ["src"]
+}

lyrics_transcriber/frontend/tsconfig.json

@@ -0,0 +1,25 @@
+{
+  "compilerOptions": {
+    "target": "ES2020",
+    "useDefineForClassFields": true,
+    "lib": ["ES2020", "DOM", "DOM.Iterable"],
+    "module": "ESNext",
+    "skipLibCheck": true,
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "resolveJsonModule": true,
+    "isolatedModules": true,
+    "noEmit": true,
+    "jsx": "react-jsx",
+    "strict": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "noFallthroughCasesInSwitch": true,
+    "baseUrl": ".",
+    "paths": {
+      "@/*": ["src/*"]
+    }
+  },
+  "include": ["src"],
+  "references": [{ "path": "./tsconfig.node.json" }]
+}

lyrics_transcriber/frontend/tsconfig.node.json

@@ -0,0 +1,23 @@
+{
+  "compilerOptions": {
+    "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.node.tsbuildinfo",
+    "target": "ES2022",
+    "lib": ["ES2023"],
+    "module": "ESNext",
+    "skipLibCheck": true,
+
+    /* Bundler mode */
+    "moduleResolution": "bundler",
+    "isolatedModules": true,
+    "moduleDetection": "force",
+    "composite": true,
+    "noEmit": false,
+
+    /* Linting */
+    "strict": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "noFallthroughCasesInSwitch": true,
+  },
+  "include": ["vite.config.ts"]
+}

lyrics_transcriber/frontend/tsconfig.tsbuildinfo

@@ -0,0 +1 @@
+{"root":["./src/app.tsx","./src/api.ts","./src/main.tsx","./src/theme.ts","./src/types.ts","./src/validation.ts","./src/vite-env.d.ts","./src/components/aifeedbackmodal.tsx","./src/components/addlyricsmodal.tsx","./src/components/agenticcorrectionmetrics.tsx","./src/components/audioplayer.tsx","./src/components/correctedwordwithactions.tsx","./src/components/correctionannotationmodal.tsx","./src/components/correctiondetailcard.tsx","./src/components/correctionmetrics.tsx","./src/components/durationtimelineview.tsx","./src/components/editactionbar.tsx","./src/components/editmodal.tsx","./src/components/edittimelinesection.tsx","./src/components/editwordlist.tsx","./src/components/fileupload.tsx","./src/components/findreplacemodal.tsx","./src/components/header.tsx","./src/components/lyricsanalyzer.tsx","./src/components/metricsdashboard.tsx","./src/components/modeselectionmodal.tsx","./src/components/modeselector.tsx","./src/components/modelselector.tsx","./src/components/previewvideosection.tsx","./src/components/referenceview.tsx","./src/components/replacealllyricsmodal.tsx","./src/components/reviewchangesmodal.tsx","./src/components/segmentdetailsmodal.tsx","./src/components/timelineeditor.tsx","./src/components/timingoffsetmodal.tsx","./src/components/transcriptionview.tsx","./src/components/worddivider.tsx","./src/components/lyricssynchronizer/synccontrols.tsx","./src/components/lyricssynchronizer/timelinecanvas.tsx","./src/components/lyricssynchronizer/upcomingwordsbar.tsx","./src/components/lyricssynchronizer/index.tsx","./src/components/shared/constants.ts","./src/components/shared/styles.ts","./src/components/shared/types.ts","./src/components/shared/components/highlightedtext.tsx","./src/components/shared/components/sourceselector.tsx","./src/components/shared/components/word.tsx","./src/components/shared/hooks/usewordclick.ts","./src/components/shared/utils/keyboardhandlers.ts","./src/components/shared/utils/localstorage.ts","./src/components/shared/utils/referencelinecalculator.ts","./src/components/shared/utils/segmentoperations.ts","./src/components/shared/utils/timingutils.ts","./src/components/shared/utils/wordutils.ts","./src/hooks/usemanualsync.ts","./src/types/global.d.ts"],"version":"5.6.3"}

lyrics_transcriber/frontend/update_version.js

@@ -0,0 +1,11 @@
+const fs = require('fs');
+const path = require('path');
+
+const packageJsonPath = path.join(__dirname, 'package.json');
+const packageJson = JSON.parse(fs.readFileSync(packageJsonPath, 'utf8'));
+
+const newVersion = process.argv[2];
+packageJson.version = newVersion;
+
+fs.writeFileSync(packageJsonPath, JSON.stringify(packageJson, null, 2) + '\n');
+console.log(`✅ Updated package.json version to ${newVersion}`);

lyrics_transcriber/frontend/vite.config.d.ts

@@ -0,0 +1,2 @@
+declare const _default: import("vite").UserConfig;
+export default _default;

lyrics_transcriber/frontend/vite.config.js

@@ -0,0 +1,10 @@
+import { defineConfig } from 'vite';
+import react from '@vitejs/plugin-react';
+// https://vite.dev/config/
+export default defineConfig({
+    plugins: [react()],
+    build: {
+        minify: false,
+        sourcemap: true,
+    }
+});

lyrics_transcriber/frontend/vite.config.ts

@@ -0,0 +1,11 @@
+import { defineConfig } from 'vite'
+import react from '@vitejs/plugin-react'
+
+// https://vite.dev/config/
+export default defineConfig({
+  plugins: [react()],
+  build: {
+    minify: false,
+    sourcemap: true,
+  }
+})