Release 20230124

* Add CSV format output in transcript, containing lines of characters formatted like: <startTime-in-integer-milliseconds>, <endTime-in-integer-milliseconds>, <transcript-including-commas>

* for easier reading by spreadsheets importing CSV, the third

column of the CSV file is delimited by quotes, and any quote
characters that might be in the transcript (which would interfere with
parsing the third column as a string) are converted to "''".

* fix syntax error

* docstring edit

Co-authored-by: Jong Wook Kim <jongwook@openai.com>
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>

.github/workflows/test.yml

@@ -23,4 +23,4 @@ jobs:
       - run: echo "$CONDA/envs/test/bin" >> $GITHUB_PATH
       - run: pip install pytest
       - run: pip install .
-      - run: pytest -k 'not test_transcribe or test_transcribe[tiny]'
+      - run: pytest --durations=0 -vv -k 'not test_transcribe or test_transcribe[tiny] or test_transcribe[tiny.en]'

tests/test_normalizer.py

@@ -84,6 +84,7 @@ def test_text_normalizer():
     assert std("he's like") == "he is like"
     assert std("she's been like") == "she has been like"
     assert std("10km") == "10 km"
+    assert std("10mm") == "10 mm"
     assert std("RC232") == "rc 232"
 
     assert (

whisper/__init__.py

@@ -94,9 +94,14 @@ def load_model(name: str, device: Optional[Union[str, torch.device]] = None, dow
     if device is None:
         device = "cuda" if torch.cuda.is_available() else "cpu"
     if download_root is None:
-        download_root = os.getenv(
+        download_root = os.path.join(
+            os.getenv(
                 "XDG_CACHE_HOME",
-            os.path.join(os.path.expanduser("~"), ".cache", "whisper")
+                os.path.join(
+                    os.path.expanduser("~"), ".cache"
+                )
+            ),
+            "whisper"
         )
 
     if name in _MODELS:

whisper/normalizers/english.json

@@ -1737,6 +1737,5 @@
     "yoghurt": "yogurt",
     "yoghurts": "yogurts",
     "mhm": "hmm",
-    "mm": "hmm",
     "mmm": "hmm"
 }

whisper/transcribe.py

@@ -1,7 +1,7 @@
 import argparse
 import os
 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
@@ -10,7 +10,7 @@ import tqdm
 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, write_txt, write_vtt, write_srt
+from .utils import exact_div, format_timestamp, make_safe, optional_int, optional_float, str2bool, get_writer
 
 if TYPE_CHECKING:
     from .model import Whisper
@@ -165,7 +165,7 @@ def transcribe(
             }
         )
         if verbose:
-            print(f"[{format_timestamp(start)} --> {format_timestamp(end)}] {text}")
+            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]
@@ -255,6 +255,7 @@ def cli():
     parser.add_argument("--model_dir", type=str, default=None, help="the path to save model files; uses ~/.cache/whisper by default")
     parser.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu", help="device to use for PyTorch inference")
     parser.add_argument("--output_dir", "-o", type=str, default=".", help="directory to save the outputs")
+    parser.add_argument("--output_format", "-f", type=str, default="all", choices=["txt", "vtt", "srt", "tsv", "json", "all"], help="format of the output file; if not specified, all available formats will be produced")
     parser.add_argument("--verbose", type=str2bool, default=True, help="whether to print out the progress and debug messages")
 
     parser.add_argument("--task", type=str, default="transcribe", choices=["transcribe", "translate"], help="whether to perform X->X speech recognition ('transcribe') or X->English translation ('translate')")
@@ -281,6 +282,7 @@ def cli():
     model_name: str = args.pop("model")
     model_dir: str = args.pop("model_dir")
     output_dir: str = args.pop("output_dir")
+    output_format: str = args.pop("output_format")
     device: str = args.pop("device")
     os.makedirs(output_dir, exist_ok=True)
 
@@ -303,22 +305,11 @@ def cli():
     from . import load_model
     model = load_model(model_name, device=device, download_root=model_dir)
 
+    writer = get_writer(output_format, output_dir)
+
     for audio_path in args.pop("audio"):
         result = transcribe(model, audio_path, temperature=temperature, **args)
-
+        writer(result, audio_path)
-        audio_basename = os.path.basename(audio_path)
-
-        # save TXT
-        with open(os.path.join(output_dir, audio_basename + ".txt"), "w", encoding="utf-8") as txt:
-            write_txt(result["segments"], file=txt)
-
-        # save VTT
-        with open(os.path.join(output_dir, audio_basename + ".vtt"), "w", encoding="utf-8") as vtt:
-            write_vtt(result["segments"], file=vtt)
-
-        # save SRT
-        with open(os.path.join(output_dir, audio_basename + ".srt"), "w", encoding="utf-8") as srt:
-            write_srt(result["segments"], file=srt)
 
 
 if __name__ == '__main__':

whisper/utils.py

@@ -1,5 +1,20 @@
+import json
+import os
+import sys
 import zlib
-from typing import Iterator, TextIO
+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):
@@ -45,14 +60,37 @@ def format_timestamp(seconds: float, always_include_hours: bool = False, decimal
     return f"{hours_marker}{minutes:02d}:{seconds:02d}{decimal_marker}{milliseconds:03d}"
 
 
-def write_txt(transcript: Iterator[dict], file: TextIO):
+class ResultWriter:
-    for segment in transcript:
+    extension: str
+
+    def __init__(self, output_dir: str):
+        self.output_dir = output_dir
+
+    def __call__(self, result: dict, audio_path: str):
+        audio_basename = os.path.basename(audio_path)
+        output_path = os.path.join(self.output_dir, audio_basename + "." + self.extension)
+
+        with open(output_path, "w", encoding="utf-8") as f:
+            self.write_result(result, file=f)
+
+    def write_result(self, result: dict, file: TextIO):
+        raise NotImplementedError
+
+
+class WriteTXT(ResultWriter):
+    extension: str = "txt"
+
+    def write_result(self, result: dict, file: TextIO):
+        for segment in result["segments"]:
             print(segment['text'].strip(), file=file, flush=True)
 
 
-def write_vtt(transcript: Iterator[dict], file: TextIO):
+class WriteVTT(ResultWriter):
+    extension: str = "vtt"
+
+    def write_result(self, result: dict, file: TextIO):
         print("WEBVTT\n", file=file)
-    for segment in transcript:
+        for segment in result["segments"]:
             print(
                 f"{format_timestamp(segment['start'])} --> {format_timestamp(segment['end'])}\n"
                 f"{segment['text'].strip().replace('-->', '->')}\n",
@@ -61,22 +99,11 @@ def write_vtt(transcript: Iterator[dict], file: TextIO):
             )
 
 
-def write_srt(transcript: Iterator[dict], file: TextIO):
+class WriteSRT(ResultWriter):
-    """
+    extension: str = "srt"
-    Write a transcript to a file in SRT format.
 
-    Example usage:
+    def write_result(self, result: dict, file: TextIO):
-        from pathlib import Path
+        for i, segment in enumerate(result["segments"], start=1):
-        from whisper.utils import write_srt
-
-        result = transcribe(model, audio_path, temperature=temperature, **args)
-
-        # save SRT
-        audio_basename = Path(audio_path).stem
-        with open(Path(output_dir) / (audio_basename + ".srt"), "w", encoding="utf-8") as srt:
-            write_srt(result["segments"], file=srt)
-    """
-    for i, segment in enumerate(transcript, start=1):
             # write srt lines
             print(
                 f"{i}\n"
@@ -86,3 +113,51 @@ def write_srt(transcript: Iterator[dict], file: TextIO):
                 file=file,
                 flush=True,
             )
+
+
+class WriteTSV(ResultWriter):
+    """
+    Write a transcript to a file in TSV (tab-separated values) format containing lines like:
+    <start time in integer milliseconds>\t<end time in integer milliseconds>\t<transcript text>
+
+    Using integer milliseconds as start and end times means there's no chance of interference from
+    an environment setting a language encoding that causes the decimal in a floating point number
+    to appear as a comma; also is faster and more efficient to parse & store, e.g., in C++.
+    """
+    extension: str = "tsv"
+
+    def write_result(self, result: dict, file: TextIO):
+        print("start", "end", "text", sep="\t", file=file)
+        for segment in result["segments"]:
+            print(round(1000 * segment['start']), file=file, end="\t")
+            print(round(1000 * segment['end']), file=file, end="\t")
+            print(segment['text'].strip().replace("\t", " "), file=file, flush=True)
+
+
+class WriteJSON(ResultWriter):
+    extension: str = "json"
+
+    def write_result(self, result: dict, file: TextIO):
+        json.dump(result, file)
+
+
+def get_writer(output_format: str, output_dir: str) -> Callable[[dict, TextIO], None]:
+    writers = {
+        "txt": WriteTXT,
+        "vtt": WriteVTT,
+        "srt": WriteSRT,
+        "tsv": WriteTSV,
+        "json": WriteJSON,
+    }
+
+    if output_format == "all":
+        all_writers = [writer(output_dir) for writer in writers.values()]
+
+        def write_all(result: dict, file: TextIO):
+            for writer in all_writers:
+                writer(result, file)
+
+        return write_all
+
+    return writers[output_format](output_dir)
+

whisper/version.py

@@ -1 +1 @@
-__version__ = "20230117"
+__version__ = "20230124"