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

WIP: Try to use multiple datasets with pruned transducer loss #245

Closed
wants to merge 10 commits into from
3 changes: 1 addition & 2 deletions egs/librispeech/ASR/pruned_transducer_stateless/train.py
Original file line number Diff line number Diff line change
Expand Up @@ -405,7 +405,7 @@ def compute_loss(
is_training: bool,
) -> Tuple[Tensor, MetricsTracker]:
"""
Compute CTC loss given the model and its inputs.
Compute transducer loss given the model and its inputs.

Args:
params:
Expand Down Expand Up @@ -599,7 +599,6 @@ def maybe_log_param_relative_changes():
)

if batch_idx % params.log_interval == 0:

if tb_writer is not None:
loss_info.write_summary(
tb_writer, "train/current_", params.batch_idx_train
Expand Down
Loading