Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Solution for Timestamps Not Appearing When Using Other Languages Like English in Korean Language Models #929

Open
THePhanT00M opened this issue Nov 25, 2024 · 2 comments

Comments

@THePhanT00M
Copy link

스크린샷 2024-11-25 오후 12 27 35

As shown in the photo, timestamps do not appear for languages other than the selected language. Is there a way to resolve this?

`args = cli()

model = whisperx.load_model("deepdml/faster-whisper-large-v3-turbo-ct2", device=args.device, device_index=list(range(2)), compute_type=args.compute_type)
audio = whisperx.load_audio(audio_path)  # 오디오 파일 로드

result = model.transcribe(audio, batch_size=args.batch_size)
language_code = result["language"]

model_a, metadata = load_align_model(language_code=language_code, device=args.device)
result = align(result["segments"], model_a, metadata, audio, device=args.device, return_char_alignments=False)

return result, language_code`
@kunho-park
Copy link

한국어 load_align_model과 영어 load_align_model 나눠서 사용하셔야 해요.

@THePhanT00M
Copy link
Author

THePhanT00M commented Dec 30, 2024

한국어 load_align_model과 영어 load_align_model 나눠서 사용하셔야 해요.

혹시 참고 할수 있는 코드가 있을까요? 단순하게 나눠서 돌리면 싱크가 이상 해져서

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants