deploy

deploy

deploy

deploy

deploy

deploy

deploy

deploy

deploy

deploy

deploy

deploy

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

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

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

docs: update timestamps API

Fix timestamps alignment call