If there are not enough credits, the bigger chunk is ignored and the smaller one is processed. Which is good. But then there is an error because the first raw transcript does not exist:
❯ transcribe https://d2mmy4gxasde9x.cloudfront.net/cast_audio/pp_48.mp3
Starting transcription for:
https://d2mmy4gxasde9x.cloudfront.net/cast_audio/pp_48.mp3
Downloading
https://d2mmy4gxasde9x.cloudfront.net/cast_audio/pp_48.mp3 to
/Users/jochen/.podcast-transcripts/pp_48/chunks/pp_48.mp3
Resampling
/Users/jochen/.podcast-transcripts/pp_48/chunks/pp_48.mp3 to
/Users/jochen/.podcast-transcripts/pp_48/chunks/pp_48_16khz.mp3
Splitting
/Users/jochen/.podcast-transcripts/pp_48/chunks/pp_48_16khz.mp3
into chunks
Converting chunk_000.mp3 chunk_001.mp3 to text
audio chunk to text:
/Users/jochen/.podcast-transcripts/pp_48/chunks/chunk_000.mp3
audio content size: 21601086
rate limit exceeded: Rate limit reached for model
`whisper-large-v3` in organization `org_01jcapvm5he8ar6kmkrhj1fd1z`
on seconds of audio per hour (ASPH): Limit 7200, Used 4847,
Requested 7199. Please try again in 40m22.583s. Visit
https://console.groq.com/docs/rate-limits for more information.
audio chunk to text:
/Users/jochen/.podcast-transcripts/pp_48/chunks/chunk_001.mp3
audio content size: 5883306
Error during transcription: [Errno 2] No such file or directory:
'/Users/jochen/.podcast-transcripts/pp_48/chunks/chunk_000.json'
Could exit more gracefully..
If there are not enough credits, the bigger chunk is ignored and the smaller one is processed. Which is good. But then there is an error because the first raw transcript does not exist:
Could exit more gracefully..