From f3b5e97e6e60a7433152a3e9df100367cd219b8c Mon Sep 17 00:00:00 2001 From: Arthur Zucker Date: Mon, 28 Nov 2022 08:32:41 +0000 Subject: [PATCH] Update README.md (#3) - Update README.md (933dd954d44445fa823390fd4ceeeed6049bcc35) Co-authored-by: Luigi Liu --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index c552083..f752cb3 100644 --- a/README.md +++ b/README.md @@ -115,7 +115,7 @@ The "<|en|>" token is used to specify that the speech is in english and should b >>> input_features = processor(ds[0]["audio"]["array"], return_tensors="pt").input_features >>> # Generate logits ->>> logits = model(input_features, decoder_input_ids = torch.tensor([[50258]]).logits +>>> logits = model(input_features, decoder_input_ids = torch.tensor([[50258]])).logits >>> # take argmax and decode >>> predicted_ids = torch.argmax(logits, dim=-1) >>> transcription = processor.batch_decode(predicted_ids)