nvidia
/

canary-1b-flash

Automatic Speech Recognition

automatic-speech-translation

hf-asr-leaderboard

Model card Files Files and versions

kunaldhawan commited on Mar 18

Commit

dcb2530

·

verified ·

1 Parent(s): ddfd59d

update compute_timestamps flag

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -366,7 +366,7 @@ python scripts/speech_to_text_aed_chunked_infer.py \
     chunk_len_in_secs=40.0 \
     batch_size=1 \
     decoding.beam.beam_size=1 \
-    compute_timestamps=False
 ```
 **Note** that for longform inference with timestamps, it is recommended to use `chunk_len_in_secs` of 10 seconds.

     chunk_len_in_secs=40.0 \
     batch_size=1 \
     decoding.beam.beam_size=1 \
+    timestamps=False
 ```
 **Note** that for longform inference with timestamps, it is recommended to use `chunk_len_in_secs` of 10 seconds.