Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-11-24 06:26:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge 91b2355c9ac2b0cf3e31f001a744066336624144 into c0d2f624c09dc18e709e37c2ad90c039a4eb72a2

Browse Source
This commit is contained in:
NITHIVARSHATP-07 2025-10-30 05:49:52 +00:00 committed by GitHub
commit bb78fe8eb6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
whisper/transcribe.py
View File

@ -260,9 +260,17 @@ def transcribe(
"no_speech_prob": result.no_speech_prob, "no_speech_prob": result.no_speech_prob,
} }
# show the progress bar when verbose is False (if True, transcribed text will be printed) # ✅ Show the progress bar only if progress_bar is True AND verbose is not enabled
show_progress = decode_options.pop("progress_bar", True)
if show_progress and (verbose is None or verbose is False):
print("🔄 Starting transcription with progress bar...")
with tqdm.tqdm( with tqdm.tqdm(
total=content_frames, unit="frames", disable=verbose is not False total=content_frames,
unit="frames",
disable=not show_progress or verbose is not False,
dynamic_ncols=True,
leave=True,
mininterval=0.1
) as pbar: ) as pbar:
last_speech_timestamp = 0.0 last_speech_timestamp = 0.0
# NOTE: This loop is obscurely flattened to make the diff readable. # NOTE: This loop is obscurely flattened to make the diff readable.
@ -564,6 +572,7 @@ def cli():
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")
parser.add_argument("--clip_timestamps", type=str, default="0", help="comma-separated list start,end,start,end,... timestamps (in seconds) of clips to process, where the last end timestamp defaults to the end of the file") parser.add_argument("--clip_timestamps", type=str, default="0", help="comma-separated list start,end,start,end,... timestamps (in seconds) of clips to process, where the last end timestamp defaults to the end of the file")
parser.add_argument("--hallucination_silence_threshold", type=optional_float, help="(requires --word_timestamps True) skip silent periods longer than this threshold (in seconds) when a possible hallucination is detected") parser.add_argument("--hallucination_silence_threshold", type=optional_float, help="(requires --word_timestamps True) skip silent periods longer than this threshold (in seconds) when a possible hallucination is detected")
parser.add_argument("--progress_bar", type=str2bool, default=True,help="Whether to show a progress bar during transcription")
# fmt: on # fmt: on
args = parser.parse_args().__dict__ args = parser.parse_args().__dict__
@ -612,7 +621,7 @@ def cli():
writer_args = {arg: args.pop(arg) for arg in word_options} writer_args = {arg: args.pop(arg) for arg in word_options}
for audio_path in args.pop("audio"): for audio_path in args.pop("audio"):
try: try:
result = transcribe(model, audio_path, temperature=temperature, **args) result = transcribe(model, audio_path,temperature=temperature,progress_bar=args.pop("progress_bar"),**args)
writer(result, audio_path, **writer_args) writer(result, audio_path, **writer_args)
except Exception as e: except Exception as e:
traceback.print_exc() traceback.print_exc()