Free Iilwimi Transcription
Bhala i-Iilwimi yesandi nevidiyo ibe ngumbhalo nge-AI. Ikhawulezayo, ichanekileyo, kwaye ikhululekile.
Indlela esebenza ngayo
- Yiya kwi- Free.ai Umshicileli
- Layisha phezulu ifayili yakho yesandi okanye yevidiyo Iilwimi
- I-AI yethu ifumanisa ngokuzenzekelayo Iilwimi kwaye ibhalela
- Layisha ezantsi i-transcript yakho njengombhalo okanye i-SRT subtitle
Iilwimi Iimpawu Zokushicilela
- ✓Isebenza nge faster- whisper (MIT licensed)
- ✓Ubhaqo oluzenzekelayo lweelwimi Iilwimi
- ✓Inkxaso ye MP3, WAV, MP4, M4A, FLAC, kunye nezinye
- ✓Ii-timestamps kunye norhwebo lwangaphandle lwesihloko esingaphantsi (SRT)
- ✓Akukho mda wobungakanani befayili kwinkqubo ehlawulweyo
- ✓Iifayile ezifihlakeleyo zigcinwa emva koqhubekeko
Iinkcukacha Zolwimi
| Iilwimi | Iilwimi |
| Ikhowudi ye-ISO | ln |
| Imodeli ye-AI | i-faster-whisper |
| Ixabiso | Iinketho zelizwe |
Iilwimi ezininzi
Bonisa Zonke IilwimiImibuzo ebuzwa rhoqo
Iilwimi yilwimi elingenazo ii-resources ze Whisper - i-large-v3-turbo ihlala ngaphezulu kwe-25% yexabiso legama lemposiso, ngamanye amaxesha iphezulu kakhulu. Ushicilelo lusetyenziswa kukukhangela kunye ne-gist kodwa alufanele luthathwe njengelulungele ukupapashwa. Ukuba i-engine ephezulu-yokuchanekileyo ifumaneka kwi-Iilwimi siyayibeka ngokuzenzekelayo.(Inqanaba D, over 25% word error rate kwiseti yexabiso elifanelekileyo - sipapasha inqanaba elithembekileyo le-WER kunokuba sibhale izibhengezo zorhwebo.)
Ewe — Iilwimi uguqulelo lutsala ukusuka kwi-token pool yakho yosuku olusimahla kuqala. Isandi sibiza malunga ne-50 tokens ngomzuzu, ngoko ke i-pool yosuku olungaziwayo igubungela iiyure ezimbalwa zesandi ngosuku. Ii-akhawunti ezibhalisiweyo zifumana i-pool enkulu kunye ne-10,000 signup tokens. Emva koko, $1 ithenga i-750,000 tokens (~ iiyure ezingama-250 zesandi).
Iilwimi iincwadi ezibhaliweyo zibuyiselwa kwi-UTF-8 eqhelekileyo ne-ortography eqhelekileyo ye-language.
I-MP3, i-WAV, i-M4A, i-FLAC, i-OGG, i-OPUS, ne-WEBM zivunyelwa ngokuthe ngqo. Kwividiyo (MP4, MOV, MKV) sikhupha umkhondo wesandi kwiseva-ecaleni phambi kokuba siyithumele kwi-Whisper — awunakutshintsha nantoni na ngokwakho. Inkqubo efanayo nokuba ithetha ntoni na ulwimi lomntu, kubandakanya Iilwimi.
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 Iilwimi zokukhuphela (ipodcasts, izifundo ezipheleleyo, iintlanganiso) zisebenza kakuhle.
Ewe - ushicilelo lwediary lomculi luyasebenza ngokumiselweyo kwi Iilwimi yonke. Imveliso ihlukaniswe njengeMculi 1 / Umculi 2 / Umculi 3 ngee-timestamps, ngoko udliwanondlebe, unxibelelwano lwepaneli, kunye neentlanganiso zeqela elininzi zibuyela emva zilabelwe. Ushicilelo lwediary luyasebenza kwimodeli eyahlukileyo kwaye lusebenza ngokufanayo kuzo zonke iilwimi esixhasayo.
Ewe — Cola i-URL kwi /transcribe/youtube/ ye-YouTube okanye /transcribe/podcast/ ye-podcast feeds (i-Apple, Spotify, RSS). Sikhuphela ezantsi isandi, siyiqhube nge-Whisper nge-language=ln, kwaye sibuyisele i-transcript ngee-timestamps kunye neelabels zomthumeli. I-Iilwimi eqhelekileyo iqulethe: iincoko, izimvo zesandi, kunye neYouTube imixholo kwi Iilwimi zonke zisebenza — dibanisa i-URL kwi /transcribe/youtube/ okanye ulayishe ifayili ngqo.
I-Whisper ibiza malunga ne-50 tokens ngomzuzu wesandi, ngoko ke urekhodo lweyure enye li ~3,000 tokens. $1 ithenga i-750,000 tokens, esebenza ngokumalunga neyure ezi-250 zesandi ngedola. Abaninzi babasebenzisi abachithanga nto - i-pool yemihla ngemihla ekhululekileyo iquka ii-clip ezimfutshane, ii-voice notes, kunye neepodcasts ezi-one-off.
Ewe — zombini i-segment-level (imizuzu nganye ~10-30) kunye ne-word-level timestamps zifumaneka. I-word-level yi-default ye-VTT/SRT subtitle export ngoko ke izihloko zihamba ngaxeshanye umgca-nge-mgca. Kwi-API misela i-timestamps="word" kwisiqu sesicelo. Iilwimi iincwadi ezibhaliweyo zibuyiselwa kwi-UTF-8 eqhelekileyo ne-ortography eqhelekileyo ye-language.
Ewe. UTHENGA umsindo (inxalenye eninzi/ifomu-data, igama lendawo "ifayile") kwi /v1/transcribe/ nge-language=ln — okanye ushiye i-parameter ye-language ukuze i-Whisper ikwazi ukuvavanya ngokuzenzekelayo. Ibuyisela i-JSON ene-transcript, ii-segments, ii-timestamps, kunye nee-labels zomthumeli. Ubhekiso olupheleleyo kunye ne-SDK snippets kwi /api/.
Ewe - xa uguqulelo lugqityiwe, nqakraza Gcina okanye uncamathisele umbhalo kwi /translate/. Iilwimi idibanisa nezinye iilwimi zonke esizixhasayo (200+). Kwiimini zengxoxo uguqulelo luya ku /summarize/; xa kuthelekiswa, thumela ku /voice/tts/ ukuvelisa isandi kwiilwimi ezilindelweyo.
Uqeqesho lwengxolo ye-Whisper lunceda ngaphantsi kulo mphakamo - i-bottleneck yinani le-Iilwimi yesandi i-Whisper yabona ngexesha loqeqesho, hayi ingxolo. Isandi esicocekileyo sestudio sihlala sibetha ingxolo yesandi, kodwa akukho nto izakufezekisa ukuthembeka oza kuyifumana kwilwimi eliphezulu lendawo.Ukuba i-transcript ibuyela ingekhoyo, thumela i-imeyili kwi contact@free.ai ngefayili — siya kubuyisela i-token kwaye sijonge ukuba i-engine eyahlukileyo iphatha isandi sakho kakuhle.