long form inference

[eschmidbauer]

Is long form inference possible with whisper_trt ?
I tried inference on 4m16s audio clip and it appeared to only transcribe 30s, here is my script:

from whisper_trt import load_trt_model

model = load_trt_model("small.en")
result = model.transcribe("test.wav")

[jaybdub]

Hi @eschmidbauer ,

It should be possible, but seems like we'll need to make some modifications to the transcribe function:

whisper_trt/whisper_trt/model.py

Line 162 in 268eff1

if int(mel.shape[2]) > whisper.audio.N_FRAMES:

Currently, it runs on a single 30s window.

John

[eschmidbauer]

It would be great to demonstrate long-form here perhaps by using sliding window