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.

Sign up for GitHub

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

Jump to bottom

Use tiktoken #1044

Merged
merged 9 commits into from
Mar 13, 2023
Merged

Use tiktoken #1044

Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
5e35893
use tiktoken==0.3.0
jongwook Mar 7, 2023
39237a3
formatting
jongwook Mar 7, 2023
67e8805
tuple should be safer
jongwook Mar 7, 2023
117ed3e
Update whisper/tokenizer.py
jongwook Mar 13, 2023
06e59be
Merge branch 'main' into use-tiktoken
jongwook Mar 13, 2023
2a14e80
use tiktoken 0.3.1
jongwook Mar 13, 2023
6869cd8
reflecting suggestions
jongwook Mar 13, 2023
72e5e67
cleanup
jongwook Mar 13, 2023
a0bd014
bypassing load_tiktoken_bpe to avoid blobfile dep
jongwook Mar 13, 2023
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
tuple should be safer
  • Loading branch information
@jongwook
jongwook committed Mar 7, 2023
commit 67e8805f24e98c515cd6e1f6ebcbe5841044ea29
12 changes: 7 additions & 5 deletions whisper/tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,14 +129,14 @@
}


@dataclass(frozen=True)
@dataclass
class Tokenizer:
"""A thin wrapper around `GPT2TokenizerFast` providing quick access to special tokens"""
jongwook marked this conversation as resolved.
Show resolved Hide resolved

encoding: tiktoken.Encoding
language: Optional[str] = None
task: Optional[str] = None
sot_sequence: List[int] = field(default_factory=list)
sot_sequence: Tuple[int] = ()
special_tokens: Dict[str, int] = field(default_factory=dict)

def __post_init__(self):
Expand All @@ -149,12 +149,14 @@ def __post_init__(self):
transcribe: int = self.special_tokens["<|transcribe|>"]

langs = tuple(LANGUAGES.keys())
self.sot_sequence.append(sot)
sot_sequence = [sot]
if self.language is not None:
self.sot_sequence.append(sot + 1 + langs.index(self.language))
sot_sequence.append(sot + 1 + langs.index(self.language))
if self.task is not None:
task_token: int = transcribe if self.task == "transcribe" else translate
self.sot_sequence.append(task_token)
sot_sequence.append(task_token)

self.sot_sequence = tuple(sot_sequence)

def encode(self, text, **kwargs):
return self.encoding.encode(text, **kwargs)
Expand Down