Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add CHiME4 recipe #746

Merged
merged 9 commits into from
Nov 19, 2021
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fix tokenizer issue for char unit
  • Loading branch information
funcwj committed Oct 29, 2021
commit 80fd5d50303533626a591b1625456668905414c2
2 changes: 2 additions & 0 deletions examples/chime4/s0/README.md
Original file line number Diff line number Diff line change
@@ -1,2 +1,4 @@
# Performance Record

TODO

4 changes: 2 additions & 2 deletions examples/chime4/s0/conf/train_conformer.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ decoder_conf:

# hybrid CTC/attention
model_conf:
ctc_weight: 0.2
ctc_weight: 0.3
lsm_weight: 0.1 # label smoothing option
length_normalized_loss: false

Expand Down Expand Up @@ -72,7 +72,7 @@ log_interval: 200

optim: adam
optim_conf:
lr: 0.0002
lr: 0.0005
scheduler: warmuplr # pytorch v1.1.0+ required
scheduler_conf:
warmup_steps: 20000
2 changes: 1 addition & 1 deletion examples/chime4/s0/run.sh
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ data_dir=data/chime4
dict=$data_dir/dict_char.txt
train_config=conf/train_conformer.yaml
exp_dir=exp/1a
decode_modes="ctc_prefix_beam_search attention"
decode_modes="ctc_prefix_beam_search attention_rescoring"
average_checkpoint=true
average_num=10

Expand Down