27.6 openai transcribe output formats

20240324

ml transcribe openai -f [json|srt|tsv|txt|vtt]

The default output format is txt, with one sentence per line. Subtitle formats are also supported, including: json, srt, tsv, and vtt. The format can be chosen with -f srt or --format=srt.

txt

ml transcribe openai jokowi.wav

Assalamu'alaikum warahmatullahi wabarakatuh, Selamat pagi, Salam sejahtera ...
Hari ini saya dengan delegasi terbatas akan berangkat ke Melbourne, Australia ...
KTT ini disenggarakan untuk memperingati 50 tahun kemitraan ASEAN dan Australia.
...

srt

A subtitle format can be selected, such as srt. Such a file can be used with a video player to show subtitles, or with ffmpeg to add subtitles to a video as in the GNU/Linux Survival Guide.

ml transcribe openai -f srt jokowi.wav

[00:00.000 --> 00:03.580]  Assalamu'alaikum warahmatullahi wabarakatuh,
[00:04.600 --> 00:07.880]  Selamat pagi, Salam sejahtera untuk kita semua.
[00:08.660 --> 00:19.240]  Hari ini saya dengan delegasi terbatas akan ...
...

json

ml transcribe openai -f json jokowi.wav

{
  "text": " Assalamu'alaikum warahmatullahi wabarakatuh, ... ",
  "segments": [{"id": 0, "seek": 0, "start": 0.0, "end": 3.58, 
                "text": " Assalamu'alaikum warahmatullahi wabarakatuh,", 
                "tokens": [50364, 6281, 23819, 84, 6, 5159, 35518, ...],
                "temperature": 0.0, "avg_logprob": -0.3409209000436883, 
                "compression_ratio": 1.5025380, "no_speech_prob": 0.0201531}, 
                {"id": 1, ...}, ... {"id": 5, ...}], 
  "language": "id"
}

tsv

ml transcribe openai -f tsv jokowi.wav

start   end     text
0       3580    Assalamu'alaikum warahmatullahi wabarakatuh,
4600    7880    Selamat pagi, Salam sejahtera untuk kita semua.
8660    19240   Hari ini saya dengan delegasi terbatas akan berangkat ke Melbourne, Australia ...
...

vtt

ml transcribe openai -f vtt jokowi.wav

WEBVTT

00:00.000 --> 00:03.580
Assalamu'alaikum warahmatullahi wabarakatuh,

00:04.600 --> 00:07.880
Selamat pagi, Salam sejahtera untuk kita semua.

00:08.660 --> 00:19.240
Hari ini saya dengan delegasi terbatas akan berangkat ke Melbourne, Australia ...

---

Your donation will support ongoing availability and give you access to the PDF version of this book. Desktop Survival Guides include Data Science, GNU/Linux, and MLHub. Books available on Amazon include Data Mining with Rattle and Essentials of Data Science. Popular open source software includes rattle, wajig, and mlhub. Hosted by Togaware, a pioneer of free and open source software since 1984. Copyright © 1995-2022 Graham.Williams@togaware.com Creative Commons Attribution-ShareAlike 4.0