Skip to content
This repository was archived by the owner on Mar 20, 2026. It is now read-only.
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
44 commits
Select commit Hold shift + click to select a range
02a4079
Add UnitY implementation
Aug 26, 2022
ff62dfe
Rename for consistency
Aug 27, 2022
122acbf
Refactor conformer encoder construction
Sep 1, 2022
65bad5c
Change the order of arguments for rdrop_alpha
Sep 1, 2022
b09a84f
Add compute_loss_with_rdrop
Sep 1, 2022
c8fa268
Move build_multitask_decoder to xm_transformer_unity.py
Sep 1, 2022
1af67c1
Fix conflict
Sep 15, 2022
e19ed1e
Fix generator selection
Sep 15, 2022
edc489c
Fix check in build_criterion
Sep 15, 2022
a7b39a8
Fix check in build_criterion
Sep 15, 2022
8f547db
Modularize Rdrop
Sep 15, 2022
31ac4b7
Minor fix
Sep 15, 2022
4fecc91
Refine class names
Sep 15, 2022
93c2ea5
Refactor submodules
Sep 15, 2022
a35d790
Fix CE
Sep 16, 2022
77efed9
Fix conflict
Sep 16, 2022
7c23030
Fix import
Sep 16, 2022
0883313
Fix argments for datasets
Sep 16, 2022
0c3e731
Add description to AugTransformerDecoderBase
Sep 16, 2022
8a3f42a
Fix SpeechToTextDatasetCreator
Sep 16, 2022
7fbcc5f
Fix conflict
Sep 20, 2022
1863f8d
Fix metavar in arguments
Sep 20, 2022
ee84288
Uncomment override_decoder_args
Sep 20, 2022
d3427df
Fix comment in warning
Sep 20, 2022
71f0b81
Add is_fisrt_pass_decoder flag
Sep 20, 2022
2f7cfed
Fix conflict
Sep 21, 2022
c6d9568
Change Translatotron2SpeechGenerator to MultiDecoderSpeechGenerator
Sep 21, 2022
bfb9b63
Move inference code to examples/speech_to_speech/unity
Sep 28, 2022
c2de124
Fix conflict
Sep 28, 2022
4c2975c
Fix rdrop default value in aux tasks
Sep 28, 2022
4a1451f
Add language tag mapping option to multitask-config-yaml
Sep 28, 2022
74c210e
Rename encoder_out2 and encoder_outs2
Sep 28, 2022
961de2e
Rename UnitYXMTransformerModel to XMTransformerModelUnitY
Sep 28, 2022
2c580c7
Support num_best_checkpoints in average_checkpoints
Sep 28, 2022
40a8a0f
Fix has_multitask
Sep 28, 2022
b41a5df
Inherit SequenceGenerator
Oct 4, 2022
e61c336
Merge remote-tracking branch 'upstream/main' into ust_unity
Oct 4, 2022
b403911
Reflect recent updates
Oct 4, 2022
05688de
Minor fix in logging
Oct 4, 2022
aa11f8d
Fix typo
Oct 4, 2022
d56ba4a
Refactor SpeechToSpectrogram2passMultitaskTaskCriterion
Oct 4, 2022
0da578a
Minor update for multitask
Oct 4, 2022
f84d5b8
Merge remote-tracking branch 'upstream/main' into ust_unity
Oct 6, 2022
56d9d65
Fix conflict
Oct 7, 2022
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
2 changes: 2 additions & 0 deletions examples/speech_to_speech/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,3 +2,5 @@
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

from . import unity # noqa
7 changes: 7 additions & 0 deletions examples/speech_to_speech/unity/__init__.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

from . import sequence_generator # noqa
from . import sequence_generator_multi_decoder # noqa
Loading