rhasspy

/

faster-whisper-medium-int8

like 1

I would also be interested in this, thanks

You can run this with faster-whisper: https://github.com/SYSTRAN/faster-whisper

Many thanks for your help @synesthesiam ! I got this working:

from faster_whisper import WhisperModel

model = WhisperModel("rhasspy/faster-whisper-medium-int8", device="cpu", compute_type="int8")
segments, info = model.transcribe("jfk.flac", beam_size=5)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))