Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
chenpangpang
transformers
Commits
619ecfe2
Unverified
Commit
619ecfe2
authored
Jan 18, 2024
by
Sanchit Gandhi
Committed by
GitHub
Jan 18, 2024
Browse files
[Whisper Tok] Move token ids to CPU when computing offsets (#28485)
* move token ids to cpu * check for torch attr
parent
0eaa5ea3
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
6 additions
and
0 deletions
+6
-0
src/transformers/models/whisper/tokenization_whisper.py
src/transformers/models/whisper/tokenization_whisper.py
+3
-0
src/transformers/models/whisper/tokenization_whisper_fast.py
src/transformers/models/whisper/tokenization_whisper_fast.py
+3
-0
No files found.
src/transformers/models/whisper/tokenization_whisper.py
View file @
619ecfe2
...
@@ -553,6 +553,9 @@ class WhisperTokenizer(PreTrainedTokenizer):
...
@@ -553,6 +553,9 @@ class WhisperTokenizer(PreTrainedTokenizer):
The time ratio to convert from token to time.
The time ratio to convert from token to time.
"""
"""
offsets
=
[]
offsets
=
[]
# ensure torch tensor of token ids is placed on cpu
if
"torch"
in
str
(
type
(
token_ids
))
and
(
hasattr
(
token_ids
,
"cpu"
)
and
callable
(
token_ids
.
cpu
)):
token_ids
=
token_ids
.
cpu
()
token_ids
=
np
.
array
(
token_ids
)
token_ids
=
np
.
array
(
token_ids
)
if
token_ids
.
shape
[
0
]
>
1
and
len
(
token_ids
.
shape
)
>
1
:
if
token_ids
.
shape
[
0
]
>
1
and
len
(
token_ids
.
shape
)
>
1
:
raise
ValueError
(
"Can only process a single input at a time"
)
raise
ValueError
(
"Can only process a single input at a time"
)
...
...
src/transformers/models/whisper/tokenization_whisper_fast.py
View file @
619ecfe2
...
@@ -248,6 +248,9 @@ class WhisperTokenizerFast(PreTrainedTokenizerFast):
...
@@ -248,6 +248,9 @@ class WhisperTokenizerFast(PreTrainedTokenizerFast):
The time ratio to convert from token to time.
The time ratio to convert from token to time.
"""
"""
offsets
=
[]
offsets
=
[]
# ensure torch tensor of token ids is placed on cpu
if
"torch"
in
str
(
type
(
token_ids
))
and
(
hasattr
(
token_ids
,
"cpu"
)
and
callable
(
token_ids
.
cpu
)):
token_ids
=
token_ids
.
cpu
()
token_ids
=
np
.
array
(
token_ids
)
token_ids
=
np
.
array
(
token_ids
)
if
token_ids
.
shape
[
0
]
>
1
and
len
(
token_ids
.
shape
)
>
1
:
if
token_ids
.
shape
[
0
]
>
1
and
len
(
token_ids
.
shape
)
>
1
:
raise
ValueError
(
"Can only process a single input at a time"
)
raise
ValueError
(
"Can only process a single input at a time"
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment