BUT-FIT
/

EBranchRegulaFormer-medium

Automatic Speech Recognition

joint_aed_ctc_speech-encoder-decoder

Model card Files Files and versions Community

Lakoc commited on Jan 22

Commit

3a631ed

•

1 Parent(s): a3404b9

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -98,7 +98,7 @@ pipe.type = "seq2seq"
 # Standard greedy decoding
 result = pipe("audio.wav")
-# Beam search decoding with joint CTC-attention scorer
 generation_config = pipe.model.generation_config
 generation_config.ctc_weight = 0.3
 generation_config.num_beams = 5

 # Standard greedy decoding
 result = pipe("audio.wav")
+# Beam search decoding with joint CTC-autoregressive scorer
 generation_config = pipe.model.generation_config
 generation_config.ctc_weight = 0.3
 generation_config.num_beams = 5