mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-26 10:16:14 +00:00
Minor fixes.
This commit is contained in:
parent
32d96002d9
commit
c24b610389
@ -24,7 +24,7 @@ on:
|
||||
types: [labeled]
|
||||
|
||||
jobs:
|
||||
run_pre_trained_conformer_ctc:
|
||||
run_pre_trained_transducer_stateless:
|
||||
if: github.event.label.name == 'ready' || github.event_name == 'push'
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
|
@ -80,7 +80,7 @@ We provide a Colab notebook to run a pre-trained RNN-T conformer model: [![Open
|
||||
Using Conformer as encoder. The decoder consists of 1 embedding layer
|
||||
and 1 convolutional layer.
|
||||
|
||||
The best WER with beam search with beam size 4 is:
|
||||
The best WER using beam search with beam size 4 is:
|
||||
|
||||
| | test-clean | test-other |
|
||||
|-----|------------|------------|
|
||||
|
@ -75,6 +75,9 @@ class Decoder(nn.Module):
|
||||
Args:
|
||||
y:
|
||||
A 2-D tensor of shape (N, U) with blank prepended.
|
||||
need_pad:
|
||||
True to left padding the input. Should be True during training.
|
||||
False to not pad the input. Used only during inference.
|
||||
Returns:
|
||||
Return a tensor of shape (N, U, embedding_dim).
|
||||
"""
|
||||
|
Loading…
x
Reference in New Issue
Block a user