Waihoki Tāhiki
Ka whakamāoritia te Tāhiki oro me te ataata ki te kupu me te AI. Āhua tere, tika, ā-waha hoki.
He pēhea te mahi
- Tere ki te Free.ai Transscriber
- Whakaata atu i tōna Tāhiki he pūoro, he pūoro rānei
- Ka kitea ā-māoritia e tātau AI a Tāhiki, ā, ka tāruatia
- Whakahua i tōna whakahua hei kupu, hei subtitles SRT rānei
Tāhiki He āhuatanga whakamāoritanga
- ✓Ka whakarewaina e te tere-whisper (MIT licensed)
- ✓Te kitenga reo Tāhiki whakamātautau
- ✓E tautoko ana i te MP3, WAV, MP4, M4A, FLAC, me ētahi atu
- ✓Ko ngā tohu wā me te kawenga subtitles (SRT)
- ✓Kāore he tepe rahi faila i runga i ngā mahere utu
- ✓Private me te haumaru -- ka tangohia nga faila i muri i te tukanga
Whakamāramatanga reo
| Reo | Tāhiki |
| ISO Code | tg |
| Tauira AI | tere ake-whisper |
| Whakahauhau | Waihoki |
He maha atu reo
Ka tirohia ngā reo katoaFAQ
Tāhiki is a less-resourced language for Whisper — large-v3-turbo sits above 25% word error rate, sometimes well above. The transcript is useful for search and gist but should not be treated as publication-ready. If a higher-accuracy engine becomes available for Tāhiki we wire it in automatically.(Tier D, over 25% word error rate i runga i ngā huinga tohu - ka whakaputaina e tātau ngā taumata WER pono i te wāhi o ngā whakapuakitanga mākete.)
He — Tāhiki te whakahua i te tuatahi mai i tōna pūngao tohu wātea i ia rā. Ko te pūoro e utu ana i ngā tohu 50 i ia minu, nō reira ko te pūngao ā-rohe e taupoki ana i ētahi wā o te oro. Ko ngā pūkete i whakaingoatia e whiwhi ana i tētahi pūngao nui ake, tae atu ki ngā tohu whakaingoatanga 10,000. I muri iho, ka hokona e $1 ngā tohu 750,000 (~250 wā o te oro).
Ko ngā whakahuatuhi Tāhiki e hoki ana ki te UTF-8 paerewa me te whakahuatuhi noa o te reo.
MP3, WAV, M4A, FLAC, OGG, OPUS, me WEBM e whakaaetia ana. Mō ngā ataata (MP4, MOV, MKV) ka tangohia e tātau te aho-pāho i mua i te tukuna ki te Whisper — kāore e hiahiatia kia tahuri e koe. He ōrite te pūtautau ahakoa te reo pūtake, tae atu ki te Tāhiki.
Ko te whakaatatanga ā-whakahaere i te āhua o te 500 MB ia pūranga. Ko ngā pūkete i whakaingoatia kia tae ki te 2 GB. Kāore he tepe uaua te roanga - ka whakawāteatia ngā pūranga roa i te wā kotahi (30-waeine ngā matapihi me te whakawāteatanga) me te whakawāteatia ki roto i tētahi tāruatanga kotahi me ngā wā whakatata. He pai te mahi o ngā pūkete Tāhiki maha-ora (pūrongo, whakaakoranga katoa, hui).
He — ko te kaikōrero diarization i runga i te pūnaha mō ia Tāhiki transcript. Ka whakawehea te huaputa hei Kaikōrero 1 / Kaikōrero 2 / Kaikōrero 3 me ngā tātaitai wā, nā reira ko ngā uiui, ngā kōrerorero papa, me ngā huinga maha-pānga e hoki ana ki te tohu. Ka haere te Diarization i runga i tētahi tauira motuhake, ā, he ōrite te mahi i ngā reo katoa e tautoko ana mātau.
He — whakataki i te URL ki roto i /transcribe/youtube/ mō YouTube, /transcribe/podcast/ rānei mō ngā pūngao podcast (Apple, Spotify, RSS). Ka whakataki tātau i te oro, ka haere mā Whisper me te reo = tg, ā, ka hoki te whakarerekētanga me ngā tātaitai wā me ngā tohu kaikōrero. Ko ngā ihirangi Tāhiki noa iho: ngā whakaakoranga, ngā uiui, ngā tuhipoka reo, me ngā ihirangi YouTube i roto i te Tāhiki katoa e mahi ana — te tāpiri i tētahi URL ki roto i /transcribe/youtube/, te whakataki rānei i te faila i te āhua tonu.
Ko te utu o te Whisper tata ki te 50 ngā tohu i ia minu o te oro, nō reira ko te whakataki o tētahi wā kotahi ~3,000 ngā tohu. $1 e hoko ana i ngā tohu 750,000, e mahi ana kia tata ki te 250 ngā wā o te oro i ia wā. Ko te nuinga o ngā kaiwhakaari kāore i te pau i tētahi mea — ko te pūtea wātea i ia rā e taupoki ana i ngā tātari poto, ngā tuhipānui reo, me ngā podcast kotahi.
He — e rua ngā taumata wā o te wāhanga (i ia ~10-30 sekone) me ngā taumata-wā o te wā e wātea ana. Ko te taumata-wā te pūmau mō te kawenga o te taitara VTT/SRT kia ōrite ai ngā tuhipoka i te raina-i-raina. I runga i te API e tautuhi ana i ngā taipitopito ="wā" i te tinana tono. Ko ngā whakahuatuhi Tāhiki e hoki ana ki te UTF-8 paerewa me te whakahuatuhi noa o te reo.
He. POST audio (maha-wāhanga/pūnaha-mātauranga, ingoa āpure "file") ki te /v1/transcribe/ me te reo=tg — ka waiho rānei te tohuāhua reo kia taea ai e Whisper te kite i te āhua o te āhua. Ka hoki mai i te JSON me te whakahua, ngā wāhanga, ngā tātaitai wā, me ngā tohu whakarongo. Ko ngā tohutoro katoa me ngā tātai SDK i te /api/.
He — ina oti te whakamāoritanga, ka kōwhiria te Whakamāori, te tāpiri rānei i te kupu ki roto i te / whakamāori /. Tāhiki e hono ana ki ētahi atu reo e tautoko ana e tātau (200+). Mō ngā wā o te hui, ka whakawātea te whakamāoritanga mā te / whakarārangi /; mō te whakamāoritanga, ka tukuna ki te / oro/tts/ hei whakamāori i te reo ūnga.
He iti iho te āwhina o te whakaakoranga hauhau a Whisper i tēnei taumata — ko te tūkino te nui o te oro Tāhiki i kitea e Whisper i te wā o te whakaakoranga, ehara i te hauhau. Ka whakaeke tonu te oro pūtautau mārō i te oro hauhau, engari kāore e tae ki te tika e whiwhi ana ki tētahi reo rawa-nui.Mēnā ka hoki mai tētahi whakahuatuhi kāore i te taea te whakamahi, te imeli ki te hoapā@free.ai me te faila — ka whakahokia e tātau ngā tohu, ā, ka tirotirohia mēnā he rerekē te mīhini e whakahaere ana i tō tātau oro.