Devanagari out, Hinglish in
Transcripts akanyorwa muDevanagari script (हिन्दी), neHindi ponctuation uye pfungwa pfungwa. Real Indian kutaura, kunyange, hazvo, haasi nyore chete Hindi — Hinglish code-switching ndechimwe chinhu, uye chimiro anobata nzira Hindi mapepanhau inoita: English mazwi uye mashoko mukati Hindi pfungwa zvinonzi
Kunyanya kutaura kwechiEnglish neHindu phrases zvakakombama muzvirongwa zviri nani kuburikidza neauto-detect uploader pahome page, iyo ichazviona sechiEnglish.
Kunyatsonzwisisa tier uye Urdu mibvunzo
Hindi iri muchikamu chepakati-pamusoro chemufananidzo uyu: mashoko anoratidza chokwadi — YouTube zvinhu, mabhuku, maintervista — anogadzira matranscripts anokosha, anenge anenge akafanana neakasiyana maEuropean languages, asi asiri akafanana neakasiyana maEuropean languages. MaHindu akataura neUrdu anosangana zvakanyanya; pane iyi peji, mazita ezvinyorwa zvinobva muUrdu anoonekwa seDevanagari, saka mazita ezvinyorwa zvinobva muUrdu anoonekwa seDevanagari, kwete Nastaliq.
Zvimwe zvinobvunzwa zvakanyanya
Chii chine mhedzisiro muDevanagari kana muLatin?
Devanagari yeHindi, Latin yekuiswa kweChirungu — nzira yekunyora Hinglish inotaridzika. Hauchazowana transcrite yakanyorwa neRomanization. Kana uchida kunyora Hindi neRomanization, transliterate the exported TXT with any Devanagari→Latin tool afterwards.
Maitiro ekuita Hinglish code-switching work?
Well — it's the defining feature of modern Hindi audio and the training data reflects that. Middle-sentence English ("basically", "presentation", full clauses") is transcribed inline in Latin script. Where it wobbles is rapid-fire switching every few words; expect the occasional wrong-script rendering to fix in the editor.
Maitiro ekunyatso kushandura kubva kuHindi kuenda kuChirungu?
Solidly kushandiswa: pachokwadi audio (podcasts, misangano, kutumira) uwane transcript kuti inofanira kuchinja pfungwa, a tier pasi pechirungu / Spanish. Regional accents kubva non-mubereki Hindi vanotaura uye heavy background mashoko kudhonza kunyatsonzwisisa pasi nekukurumidza kupfuura zvavanoita for English.
Chii nezve Urdu — imwe chete rurimi rwakataurwa, imwe chete script?
Mutauro weHindustani unotaura unotaurawo, uye mufananidzo unonyora mashoko eUrdu-register here — asi muDevanagari, sezvo iyi peji ichipinza Hindi. Kuti uwane maUrudhi muNastaliq/Arabic script, uenderere mberi nekumhara peji uye pinza Urdu (ur) musarudzo.
Hindi audio kune English text?
Izvi peji inogadzira Hindi transcript — yakakwana nhanho. Export TXT uye machine-kushandura kwechirungu; hi→en kushandura pa text yakachena ndicho chikuru. One-shot kushandura kutaura anorasikirwa zvakawanda, kunyanya pa code-switched zvinhu. In-app kushandura iri kutarisirwa.
Do Bollywood mashoko kana bhajans transcribe?
Kutaura ndechinangwa chekugadzirwa; kutamba ndechinangwa chekushanda. Kutaura kwakajeka kunobuda zvakanaka, asi mavhidhiyo emitambo ane mazita akazara anoita seanotadza. Mavhidhiyo emashoko, maintervista, uye mavlogs anoshandurwa sezvavanotaura.