msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

Update chunk_decode.yaml

Browse Source
pull/1319/head
Jackwaterveg 3 years ago committed by GitHub
parent c893d0d828
commit e7189b216c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File

4
examples/aishell/asr1/conf/tuning/chunk_decode.yaml
Unescape View File

@ -3,9 +3,9 @@ decode_batch_size: 128
error_rate_type: cer error_rate_type: cer
decoding_method: attention # 'attention', 'ctc_greedy_search', 'ctc_prefix_beam_search', 'attention_rescoring' decoding_method: attention # 'attention', 'ctc_greedy_search', 'ctc_prefix_beam_search', 'attention_rescoring'
ctc_weight: 0.5 # ctc weight for attention rescoring decode mode. ctc_weight: 0.5 # ctc weight for attention rescoring decode mode.
decoding_chunk_size: -1 # decoding chunk size. Defaults to -1. decoding_chunk_size: 16 # decoding chunk size. Defaults to -1.
# <0: for decoding, use full chunk. # <0: for decoding, use full chunk.
# >0: for decoding, use fixed chunk size as set. # >0: for decoding, use fixed chunk size as set.
# 0: used for training, it's prohibited here. # 0: used for training, it's prohibited here.
num_decoding_left_chunks: -1 # number of left chunks for decoding. Defaults to -1. num_decoding_left_chunks: -1 # number of left chunks for decoding. Defaults to -1.
simulate_streaming: False # simulate streaming inference. Defaults to False. simulate_streaming: True # simulate streaming inference. Defaults to False.

Write Preview
Loading…
Cancel
Save