Uguqulelo lwe-Urdu olukhululekileyo
Uguqulelo lwe-Urdu lwesandi nevidiyo kumbhalo nge-AI. Ikhawulezayo, ichanekileyo, kwaye ikhululekile.
Indlela esebenza ngayo
- Yiya kwi- Free.ai Umshicileli
- Layisha phezulu ifayili yakho yevidiyo okanye yesandi ye-Urdu
- I-AI yethu ifumanisa ngokuzenzekelayo i-Urdu kwaye ibhalela
- Layisha ezantsi i-transcript yakho njengombhalo okanye i-SRT subtitle
Urdu Iimpawu Zokushicilela
- ✓Isebenza ngu faster-whisper (MIT ilayisensiwe)
- ✓Ubhaqo oluzenzekelayo lweelwimi lweUrdu
- ✓Inkxaso ye MP3, WAV, MP4, M4A, FLAC, kunye nezinye
- ✓Ii-timestamps kunye norhwebo lwangaphandle lwesihloko esingaphantsi (SRT)
- ✓Akukho mda wobungakanani befayili kwinkqubo ehlawulweyo
- ✓Private and secure -- files are deleted after processing
Iinkcukacha Zolwimi
| Iilwimi | Urdu |
| Ikhowudi ye ISO | ur |
| Imodeli ye-AI | _Iifayile: |
| Ixabiso | Iinketho ze-GNU/Linux |
Iilwimi ezininzi
Bonisa Zonke IilwimiImibuzo ebuzwa rhoqo
Urdu yindawo ephakathi- yomthombo wegama le Whisper - enkulu- v3- iinqanawa ezihambayo kwi 15- 25% igama lomyinge woxinzelelo lomonakalo. Isiseko soshicilelo luthembekile; lindele igama- elibizwa- ngento iimpazamo, ikhowudi- etshintshayo i glitches, ne short- uthetha- uthetha misfires. Phanda i pass yomuntu yoshicilelo- umgangatho wemveliso.(Inqanaba C, 15-25% word error rate kwiseti ye-benchmark - sipapasha inqanaba elilungileyo le-WER kunokuba siqinisekise ukuthengisa.)
Ewe — Urdu ukudlulisa kuqala kusuka kwi-token pool yakho yosuku olusimahla. Isandi sibiza malunga ne-token 50 ngomzuzu, ngoko ke i-token pool yosuku olungaziwayo igubungela iiyure ezimbalwa zesandi ngosuku. Ii-akhawunti ezibhalisiweyo zifumana i-token pool enkulu ye-30,000-token ngosuku. Emva koko, ukudlulisa kuhlawulwe-njengoko-uhamba, nge-token top-ups ukusuka kwi-$1.
Urdu iincwadana zibuyiselwa kwiskripthi yazo esemthethweni ekunene- ukuya ekhohlo kwaye zibonise ngokuchanekileyo nakweyiphi na imboniselo ye RTL- eyaziyo (iziphene, i Word, i Google Docs).
MP3, WAV, M4A, FLAC, OGG, OPUS, ne WEBM zivunyelwa ngokuthe ngqo. Kwividiyo (MP4, MOV, MKV) sikhupha umculo osuka kumncedisi-ecaleni phambi kokuba siyithumelele kwi Whisper - awunakutshintsha nantoni na ngokwakho. Inkqubo efanayo yokuhambisa ngaphandle kolwazi lomntu ovela kulo, kubandakanya i Urdu.
Ukhuphelo olungaziwayo luya kufikelela kwi-500 MB kwifayili nganye. Ii-akhawunti ezibhalisiweyo ziye kwi-2 GB. Ukuphela kwexesha alikho umda onzima - iifayile ezide ziqhutywa ngokuzenzekelayo (iifestile zemizuzu engama-30 ezinamathele) kwaye zidityaniswe kwakhona kwi-transcript epheleleyo enee-timestamps eziqhubekayo. Iiyure ezininzi Urdu zokukhuphela (ipodcasts, izifundo ezipheleleyo, iintlanganiso) zisebenza kakuhle.
Ewe - ushicilelo lomculi luyasebenza ngokungagqibekanga kulo lonke ushicilelo lwe Urdu. Imveliso ihlukaniswe njenge Umculi 1 / Umculi 2 / Umculi 3 ngexesha elimiselweyo, ngoko udliwanondlebe, uxoxo lwepaneli, kunye neentlanganiso zeqela elininzi zibuyela umva zilabelwe. Ushicilelo luyasebenza kwimodeli eyahlukileyo kwaye lusebenza ngokufanayo kuzo zonke iilwimi esixhasayo.
Ewe - cofa i URL kwi /transcribe/youtube/ yeYouTube okanye /transcribe/podcast/ yepodcast feeds (Apple, Spotify, RSS). Sikhuphela umsindo, siqhuba nge Whisper nge ulwimi=ur, kwaye sibuyisela uguqulelo ngee-timestamps kunye neelabels zomthumeli. Izinto eziqhelekileyo ze Urdu: I-WhatsApp voice notes, YouTube vlogs, and short-form video are the most common Urdu workloads - paste a URL into /transcribe/youtube/ or upload the audio directly.
Whisper ibiza malunga ne-50 tokens ngomzuzu wesandi, ngoko urekhodo lweyure enye luyi ~3,000 tokens. Abaninzi abasebenzisi abachithanga nto - i-pool yemihla ngemihla ekhululekileyo ye-30,000 tokens iquka iiclip ezimfutshane, ii-voice notes, kunye ne-one-off podcasts. Ngapha koko, ukudlulisa kuhlawulwe-njengoko-uhamba, nge-token top-ups ukusuka kwi $1.
Ewe - zombini inqanaba lecandelo (imini nganye ~10-30 imizuzwana) kunye nexesha legama eliphakamileyo lifumaneka. Igama-lomgangatho lumiselwe kwi-VTT/SRT imveliso yesicatshulwa ukuze izihloko zidityaniswe umgca-nge-umgca. Kwi-API misela i-timestamps="igama" kwisiqu sesicelo. Urdu iincwadana zibuyiselwa kwiskripthi yazo esemthethweni ekunene- ukuya ekhohlo kwaye zibonise ngokuchanekileyo nakweyiphi na imboniselo ye RTL- eyaziyo (iziphene, i Word, i Google Docs).
Ewe. UTHANDA umsindo (inxalenye eninzi/ifomu-data, igama lendawo "ifayile") kwi /v1/transcribe / nge-language=ur - okanye ushiye iparameter ye-language ukuze i-Whisper ifumane ngokuzenzekelayo. Ibuyisela i-JSON nge-transcript, ii-segments, i-timestamps, kunye nee-labels zomthumeli. Ubhekiso olupheleleyo kunye ne-SDK snippets kwi /api/.
Ewe - xa uguqulelo lugqityiwe, nqakraza Gcina okanye uncamathisele umbhalo kwi /translate/. Urdu idibanisa nezinye iilwimi zonke esizixhasayo (200+). Kwiimini zengxoxo uguqulelo luya ku /summarize/; xa kuthelekiswa, thumela ku /voice/tts/ ukuvelisa isandi kwiilwimi ezilindelweyo.
Whisper' s noise robustness still applies on Urdu, but at this accuracy level any extra noise compounds the baseline error rate. Clean headset audio gives noticeably better results than phone or laptop- mic recordings.Ukuba ushicilelo luya buyela ngaphandle kokusebenziswa, thumela i-imeyili contact@free.ai ngefayili - siya kubuyisela i-token kwaye sijonge ukuba i-engine eyahlukileyo iphatha isandi sakho kakuhle.