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 pull request #549 from amolinasalazar/minor_fixes

Browse Source 
Minor fixes for word options and subtitles
This commit is contained in:
Max Bain
2023-10-31 12:26:47 -07:00
committed by GitHub
parent dbeb8617f2 d4a600b568
commit 6b1100a919
2 changed files with 3 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
whisperx/transcribe.py
View File

@ -67,8 +67,8 @@ def cli():
parser.add_argument("--no_speech_threshold", type=optional_float, default=0.6, help="if the probability of the <|nospeech|> token is higher than this value AND the decoding has failed due to `logprob_threshold`, consider the segment as silence") parser.add_argument("--no_speech_threshold", type=optional_float, default=0.6, help="if the probability of the <|nospeech|> token is higher than this value AND the decoding has failed due to `logprob_threshold`, consider the segment as silence")
parser.add_argument("--max_line_width", type=optional_int, default=None, help="(not possible with --no_align) the maximum number of characters in a line before breaking the line") parser.add_argument("--max_line_width", type=optional_int, default=None, help="(not possible with --no_align) the maximum number of characters in a line before breaking the line")
parser.add_argument("--max_line_count", type=optional_int, default=None, help="(requires --no_align) the maximum number of lines in a segment") parser.add_argument("--max_line_count", type=optional_int, default=None, help="(not possible with --no_align) the maximum number of lines in a segment")
parser.add_argument("--highlight_words", type=str2bool, default=False, help="(requires --word_timestamps True) underline each word as it is spoken in srt and vtt") parser.add_argument("--highlight_words", type=str2bool, default=False, help="(not possible with --no_align) underline each word as it is spoken in srt and vtt")
parser.add_argument("--segment_resolution", type=str, default="sentence", choices=["sentence", "chunk"], help="(not possible with --no_align) the maximum number of characters in a line before breaking the line") parser.add_argument("--segment_resolution", type=str, default="sentence", choices=["sentence", "chunk"], help="(not possible with --no_align) the maximum number of characters in a line before breaking the line")
parser.add_argument("--threads", type=optional_int, default=0, help="number of threads used by torch for CPU inference; supercedes MKL_NUM_THREADS/OMP_NUM_THREADS") parser.add_argument("--threads", type=optional_int, default=0, help="number of threads used by torch for CPU inference; supercedes MKL_NUM_THREADS/OMP_NUM_THREADS")
@ -157,7 +157,7 @@ def cli():
if no_align: if no_align:
for option in word_options: for option in word_options:
if args[option]: if args[option]:
parser.error(f"--{option} requires --word_timestamps True") parser.error(f"--{option} not possible with --no_align")
if args["max_line_count"] and not args["max_line_width"]: if args["max_line_count"] and not args["max_line_width"]:
warnings.warn("--max_line_count has no effect without --max_line_width") warnings.warn("--max_line_count has no effect without --max_line_width")
writer_args = {arg: args.pop(arg) for arg in word_options} writer_args = {arg: args.pop(arg) for arg in word_options}

3
whisperx/utils.py
View File

@ -226,9 +226,6 @@ class SubtitlesWriter(ResultWriter):
highlight_words: bool = options["highlight_words"] highlight_words: bool = options["highlight_words"]
max_line_width = 1000 if raw_max_line_width is None else raw_max_line_width max_line_width = 1000 if raw_max_line_width is None else raw_max_line_width
preserve_segments = max_line_count is None or raw_max_line_width is None preserve_segments = max_line_count is None or raw_max_line_width is None
if len(result["segments"]) == 0:
return
if len(result["segments"]) == 0: if len(result["segments"]) == 0:
return return