chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 18:17:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into silero-vad

Browse Source
This commit is contained in:
Max Bain
2025-01-11 17:05:53 +00:00
committed by GitHub
parent 79eb8fa53d 734084cdf6
commit c288f4812a
3 changed files with 41 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
whisperx/asr.py
View File

@ -1,5 +1,7 @@
import os
from typing import List, Optional, Union
import warnings
from typing import List, NamedTuple, Optional, Union
from dataclasses import replace
import ctranslate2
import faster_whisper
@ -247,7 +249,7 @@ class FasterWhisperPipeline(Pipeline):
print(f"Suppressing numeral and symbol tokens")
new_suppressed_tokens = numeral_symbol_tokens + self.options.suppress_tokens
new_suppressed_tokens = list(set(new_suppressed_tokens))
self.options = self.options._replace(suppress_tokens=new_suppressed_tokens)
self.options = replace(self.options, suppress_tokens=new_suppressed_tokens)
segments: List[SingleSegment] = []
batch_size = batch_size or self._batch_size
@ -276,7 +278,7 @@ class FasterWhisperPipeline(Pipeline):
# revert suppressed tokens if suppress_numerals is enabled
if self.suppress_numerals:
self.options = self.options._replace(suppress_tokens=previous_suppress_tokens)
self.options = replace(self.options, suppress_tokens=previous_suppress_tokens)
return {"segments": segments, "language": language}