langtech-veu
/

faster-whisper-timestamped-cs

Automatic Speech Recognition

whisper-large-v3

Model card Files Files and versions

AbirMessaoudi commited on Oct 16

Commit

abddac8

·

verified ·

1 Parent(s): cb4e10c

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -75,7 +75,7 @@ model = WhisperModel(model_size, device="cuda", compute_type="float16")
 # or run on CPU with INT8
 # model = WhisperModel(model_size, device="cpu", compute_type="int8")
-segments, info = model.transcribe("audio.mp3", beam_size=5, task="transcribe")
 for segment in segments:
     print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
 ```

 # or run on CPU with INT8
 # model = WhisperModel(model_size, device="cpu", compute_type="int8")
+segments, info = model.transcribe("audio.mp3", task="transcribe")
 for segment in segments:
     print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
 ```