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

Write each sentence as a separate line for the txt output (#101)

Browse Source 
* Write each sentence as a separate line for the txt output

Write each sentence as a separate line for the txt output

* Update utils.py

Co-authored-by: EliEron <example@example.com>
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
This commit is contained in:
EliEron
2022-09-26 13:52:28 +02:00
committed by GitHub
parent 520796a34c
commit fc0f40981d
2 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
whisper/transcribe.py
View File

@@ -10,7 +10,7 @@ import tqdm
from .audio import SAMPLE_RATE, N_FRAMES, HOP_LENGTH, pad_or_trim, log_mel_spectrogram from .audio import SAMPLE_RATE, N_FRAMES, HOP_LENGTH, pad_or_trim, log_mel_spectrogram
from .decoding import DecodingOptions, DecodingResult from .decoding import DecodingOptions, DecodingResult
from .tokenizer import LANGUAGES, TO_LANGUAGE_CODE, get_tokenizer from .tokenizer import LANGUAGES, TO_LANGUAGE_CODE, get_tokenizer
from .utils import exact_div, format_timestamp, optional_int, optional_float, str2bool, write_vtt, write_srt from .utils import exact_div, format_timestamp, optional_int, optional_float, str2bool, write_txt, write_vtt, write_srt
if TYPE_CHECKING: if TYPE_CHECKING:
from .model import Whisper from .model import Whisper
@@ -295,7 +295,7 @@ def cli():
# save TXT # save TXT
with open(os.path.join(output_dir, audio_basename + ".txt"), "w", encoding="utf-8") as txt: with open(os.path.join(output_dir, audio_basename + ".txt"), "w", encoding="utf-8") as txt:
print(result["text"], file=txt) write_txt(result["segments"], file=txt)
# save VTT # save VTT
with open(os.path.join(output_dir, audio_basename + ".vtt"), "w", encoding="utf-8") as vtt: with open(os.path.join(output_dir, audio_basename + ".vtt"), "w", encoding="utf-8") as vtt:

5
whisper/utils.py
View File

@@ -44,6 +44,11 @@ def format_timestamp(seconds: float, always_include_hours: bool = False):
return f"{hours_marker}{minutes:02d}:{seconds:02d}.{milliseconds:03d}" return f"{hours_marker}{minutes:02d}:{seconds:02d}.{milliseconds:03d}"
def write_txt(transcript: Iterator[dict], file: TextIO):
for segment in transcript:
print(segment['text'].strip(), file=file, flush=True)
def write_vtt(transcript: Iterator[dict], file: TextIO): def write_vtt(transcript: Iterator[dict], file: TextIO):
print("WEBVTT\n", file=file) print("WEBVTT\n", file=file)
for segment in transcript: for segment in transcript: