From 4ee147ca599856d68a493ef93c912313b34f4e4f Mon Sep 17 00:00:00 2001
From: Jong Wook Kim <jongwook@nyu.edu>
Date: Tue, 24 Jan 2023 10:07:23 -0800
Subject: [PATCH] handle printing even if sys.stdout.buffer is not available

---
 whisper/transcribe.py | 11 +++--------
 whisper/utils.py      | 13 +++++++++++++
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/whisper/transcribe.py b/whisper/transcribe.py
index c0404416e..c5bea7b26 100644
--- a/whisper/transcribe.py
+++ b/whisper/transcribe.py
@@ -1,8 +1,7 @@
 import argparse
 import os
-import sys
 import warnings
-from typing import List, Optional, Tuple, Union, TYPE_CHECKING
+from typing import Optional, Tuple, Union, TYPE_CHECKING
 
 import numpy as np
 import torch
@@ -11,7 +10,7 @@
 from .audio import SAMPLE_RATE, N_FRAMES, HOP_LENGTH, pad_or_trim, log_mel_spectrogram
 from .decoding import DecodingOptions, DecodingResult
 from .tokenizer import LANGUAGES, TO_LANGUAGE_CODE, get_tokenizer
-from .utils import exact_div, format_timestamp, optional_int, optional_float, str2bool, get_writer
+from .utils import exact_div, format_timestamp, make_safe, optional_int, optional_float, str2bool, get_writer
 
 if TYPE_CHECKING:
     from .model import Whisper
@@ -166,11 +165,7 @@ def add_segment(
             }
         )
         if verbose:
-            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.stdout.buffer.write(line.encode(sys.getdefaultencoding(), errors="replace"))
-            sys.stdout.flush()
+            print(make_safe(f"[{format_timestamp(start)} --> {format_timestamp(end)}] {text}"))
 
     # show the progress bar when verbose is False (otherwise the transcribed text will be printed)
     num_frames = mel.shape[-1]
diff --git a/whisper/utils.py b/whisper/utils.py
index 8293641b2..5dacc173c 100644
--- a/whisper/utils.py
+++ b/whisper/utils.py
@@ -1,8 +1,21 @@
 import json
 import os
+import sys
 import zlib
 from typing import Callable, TextIO
 
+system_encoding = sys.getdefaultencoding()
+
+if system_encoding != "utf-8":
+    def make_safe(string):
+        # replaces any character not representable using the system default encoding with an '?',
+        # avoiding UnicodeEncodeError (https://github.com/openai/whisper/discussions/729).
+        return string.encode(system_encoding, errors="replace").decode(system_encoding)
+else:
+    def make_safe(string):
+        # utf-8 can encode any Unicode code point, so no need to do the round-trip encoding
+        return string
+
 
 def exact_div(x, y):
     assert x % y == 0