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

add translate, fix word_timestamp error

Browse Source
This commit is contained in:
Max Bain
2023-05-13 12:14:06 +01:00
parent 4603f010a5
commit fd8f1003cf
5 changed files with 17 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
whisperx/transcribe.py
View File

@ -86,6 +86,11 @@ def cli():
align_model: str = args.pop("align_model")
interpolate_method: str = args.pop("interpolate_method")
no_align: bool = args.pop("no_align")
task : str = args.pop("task")
if task == "translate":
# translation cannot be aligned
no_align = True
return_char_alignments: bool = args.pop("return_char_alignments")
hf_token: str = args.pop("hf_token")
@ -139,7 +144,7 @@ def cli():
results = []
tmp_results = []
# model = load_model(model_name, device=device, download_root=model_dir)
model = load_model(model_name, device=device, compute_type=compute_type, language=args['language'], asr_options=asr_options, vad_options={"vad_onset": vad_onset, "vad_offset": vad_offset},)
model = load_model(model_name, device=device, compute_type=compute_type, language=args['language'], asr_options=asr_options, vad_options={"vad_onset": vad_onset, "vad_offset": vad_offset}, task=task)
for audio_path in args.pop("audio"):
audio = load_audio(audio_path)