Delete bench_wraparound.py

Upload folder using huggingface_hub

Upload folder using huggingface_hub

feat(aligner): group missing-words pairs under shared border

feat(aligner): group missing-words pairs into shared border

perf: eliminate mode-switch lag — clear all audio on toggle

perf: eliminate double round-trip delay on audio input

refactor: simplify link panel — always-visible download button

feat: add /process_url_session API endpoint for URL-based alignment

fix: simplify link panel download flow — animate button directly

fix: use gr.Group for input panels and add changelog emoji;docs: update changelog — settings auto-collapse feat: auto-collapse settings accordions after extraction

Upload folder using huggingface_hub

docs: update changelog and fix API docs TOC;fix: polish input UI — inline errors, example waveform, scrollbar

docs: add changelog system — user-facing, API, and technical;feat: improve URL input UX — audio player, domain warnings, smart extract button

feat: redesign audio input as Link/Upload/Record toggle;perf: use per-segment WAVs and skip audio I/O for API calls

fix: cache audio in-process dict to avoid Gradio State deep-copy OOM

fix: combine yt-dlp metadata and download into single call

feat: add diagnostic logging for render and WAV write;feat: add audio duration warning on upload feat: add YouTube PO token server for yt-dlp on datacenter IPs

feat: add URL input for yt-dlp audio download;perf: defer char spans to MFA injection — reduce initial HTML size

perf: use single full.wav + media fragments — eliminate 796 per-segment file writes

perf: switch segment audio to OGG and remove inline base64 — fix long recording crash;fix: cap ZeroGPU lease duration at 120s hard limit

refactor: rename quran_multi_aligner and dataset folders to match project identity

docs: update API link path and trim SVG footer

fix: update API and feedback links to GitHub repo

Add LICENSE file reference to space entry points

Add license headers to space entry points

Pin torchaudio==2.8.0 to fix CUDA runtime mismatch on ZeroGPU

update README.md

update README.md

Increase CPU subprocess timeout from 10min to 2h for long recordings

Update config.py

docs: update timestamps API

Merge branch 'main' of https://huggingface.co/spaces/hetchyy/Quran-multi-aligner

Update lease durations

Update config.py

Fix timestamps alignment call

Fix timestamps computation error

Add token parameter

Fix CPU bug

Update imports

Update Client API

Update quranic phonemizer package

Update API doc

Fix GPU VRAM logging: capture stats inside lease before ZeroGPU reclaims

Update walltime estimation

Update config

Usage logging V2: grouped JSON schema, endpoint tracking, GPU profiling

Fix VRAM stats crash on ZeroGPU after lease ends

Reorganize client API docs with table of contents and grouped sections

Fix GPU info log: use total_memory instead of total_mem