Inference on long files about faster-whisper

[guillaumekln]

Yes, the transcription time depends on the audio file duration. Long files will take longer.

[guillaumekln]

Try running the model with 8-bit quantization:

model = WhisperModel(model_path, device="cuda", compute_type="int8")

[guillaumekln]

Hi,

The Whisper transcription loop already handles long files using a sliding 30-second window while keeping the context. So you don't need to do anything to transcribe long files.

[databill86]

Thank you. So is it normal that the transcription time is considerably long for long files ?

[databill86]

Sorry I closed and reopened the issue. I just have one last thing about the longer files.
If we use the "gpu" as a device, is there any way we can avoid OOM for these longer files ?

[guillaumekln]

What is your GPU and what model size are you running?

[databill86]

It's a NVIDIA GeForce GTX 1070 Ti 8Go, I was running the large-v2 model on a 18min file. But even with 4min file I have OOM.

[databill86]

Wow, just like that! it's a lot faster, and no OOM!!!
Thank you!
I will close the issue now for good :)