chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 18:17:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #309 from Ca-ressemble-a-du-fake/patch-1

Browse Source 
Add Audacity export
This commit is contained in:
Max Bain
2023-06-07 11:50:05 +01:00
committed by GitHub
parent 0c84c26d92 d39c1b2319
commit f9c5ff9f08
2 changed files with 30 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
whisperx/transcribe.py
View File

@ -26,7 +26,7 @@ def cli():
parser.add_argument("--compute_type", default="float16", type=str, choices=["float16", "float32", "int8"], help="compute type for computation")
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=["all", "srt", "vtt", "txt", "tsv", "json"], help="format of the output file; if not specified, all available formats will be produced")
parser.add_argument("--output_format", "-f", type=str, default="all", choices=["all", "srt", "vtt", "txt", "tsv", "json", "aud"], 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')")

27
whisperx/utils.py
View File

@ -365,6 +365,28 @@ class WriteTSV(ResultWriter):
print(round(1000 * segment["end"]), file=file, end="\t")
print(segment["text"].strip().replace("\t", " "), file=file, flush=True)
class WriteAudacity(ResultWriter):
"""
Write a transcript to a text file that audacity can import as labels.
The extension used is "aud" to distinguish it from the txt file produced by WriteTXT.
Yet this is not an audacity project but only a label file!
Please note : Audacity uses seconds in timestamps not ms!
Also there is no header expected.
If speaker is provided it is prepended to the text between double square brackets [[]].
"""
extension: str = "aud"
def write_result(self, result: dict, file: TextIO, options: dict):
ARROW = " "
for segment in result["segments"]:
print(segment["start"], file=file, end=ARROW)
print(segment["end"], file=file, end=ARROW)
print( ( ("[[" + segment["speaker"] + "]]") if "speaker" in segment else "") + segment["text"].strip().replace("\t", " "), file=file, flush=True)
class WriteJSON(ResultWriter):
extension: str = "json"
@ -383,6 +405,9 @@ def get_writer(
"tsv": WriteTSV,
"json": WriteJSON,
}
optional_writers = {
"aud": WriteAudacity,
}
if output_format == "all":
all_writers = [writer(output_dir) for writer in writers.values()]
@ -393,6 +418,8 @@ def get_writer(
return write_all
if output_format in optional_writers:
return optional_writers[output_format](output_dir)
return writers[output_format](output_dir)
def interpolate_nans(x, method='nearest'):