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

Enable Hebrew support

Browse Source
This commit is contained in:
aramlang
2023-05-03 11:26:12 -05:00
parent 9fb51412c0
commit cb53661070
1 changed files with 8 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
whisperx/alignment.py
View File

@ -38,6 +38,7 @@ DEFAULT_ALIGN_MODELS_HF = {
"fa": "jonatasgrosman/wav2vec2-large-xlsr-53-persian",
"el": "jonatasgrosman/wav2vec2-large-xlsr-53-greek",
"tr": "mpoyraz/wav2vec2-xls-r-300m-cv7-turkish",
"he": "imvladikon/wav2vec2-xls-r-300m-hebrew",
}
@ -231,8 +232,13 @@ def align(
emission = emissions[0].cpu().detach()
trellis = get_trellis(emission, tokens)
path = backtrack(trellis, emission, tokens)
blank_id = 0
for char, code in model_dictionary.items():
if char == '[pad]' or char == '<pad>':
blank_id = code
trellis = get_trellis(emission, tokens, blank_id)
path = backtrack(trellis, emission, tokens, blank_id)
if path is None:
print(f'Failed to align segment ("{segment["text"]}"): backtrack failed, resorting to original...')
break