heimoshuiyu/whisper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

print '?' if a letter can't be encoded using the system default encoding (#859)

Browse Source
This commit is contained in:
Jong Wook Kim
2023-01-17 23:28:36 -08:00
committed by GitHub
parent 37a4f1be6d
commit 9d646db9d8
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
whisper/transcribe.py
View File

@@ -1,5 +1,6 @@
import argparse import argparse
import os import os
import sys
import warnings import warnings
from typing import List, Optional, Tuple, Union, TYPE_CHECKING from typing import List, Optional, Tuple, Union, TYPE_CHECKING
@@ -165,7 +166,10 @@ def transcribe(
} }
) )
if verbose: if verbose:
print(f"[{format_timestamp(start)} --> {format_timestamp(end)}] {text}") line = f"[{format_timestamp(start)} --> {format_timestamp(end)}] {text}\n"
# compared to just `print(line)`, this replaces any character not representable using
# the system default encoding with an '?', avoiding UnicodeEncodeError.
sys.stderr.buffer.write(line.encode(sys.getdefaultencoding(), errors="replace"))
# show the progress bar when verbose is False (otherwise the transcribed text will be printed) # show the progress bar when verbose is False (otherwise the transcribed text will be printed)
num_frames = mel.shape[-1] num_frames = mel.shape[-1]