what is the max length of the audio file i can transcribe with this model ?
#4
by
stephenfernandess
- opened
given that the model and extrapolate upto 32k inout context length.
What is the max audio length i can use to generate transcription.
on that note, please can someone share some code on long format transcription of audio files.
Hi
@stephenfernandess
. Apologies for late response . Audio clips of up to 30 seconds are recommended, but you can process longer lengths, up to the size of the model's context window subtracting the output tokens you request. Please check this to get started. https://ai.google.dev/gemma/docs/capabilities/audio
Thank you