Hi, i am tryin to generate subtitles from an audio size of 17mb, and i do not know why, i just get the first phrase of audio, this is my code and response:
import openai
openai.api_key = “xxxxxx”
audio_intro = R’path to .mp3’
#openai.api_key = os.getenv(“OPENAI_API_KEY”)
audio_file = open(audio_intro, “rb”)
transcript = openai.Audio.transcribe(“whisper-1”, audio_file, response_format=“srt”, temperature=0.2, language = “en”)
response :
I’m having the exact same problem. Did you ever figure this out?
I have never used Whisper before but given the fact that multiple people are having the same error (not sure about before this) it may just be an API error. Lets hope someone more experienced with this comes in.
what I’m reading is that the “ideal” input is 30 seconds, if you have access to the source files then you could split it by some factor like length of silence; but for other conditions perhaps overlapping chunks might be more efficient and perhaps using gpt to consolidate those crunks into the most coherent output;
edit: in hindsight this doesn’t actually seem to address the question at all, I think I misread the OP, sorry about that.
