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

处理过程会越来越慢,不知道为什么。 #282

Open
terryleo88 opened this issue Jan 28, 2025 · 1 comment
Open

处理过程会越来越慢,不知道为什么。 #282

terryleo88 opened this issue Jan 28, 2025 · 1 comment
Labels
question Further information is requested

Comments

@terryleo88
Copy link

🤔 问题描述 Problem Description

看一下下面的日志,前面使用cuda,超快的处理了声音,然后到了开始transcription的时候,开始速度很快,然后越来越慢。

MDX Kim_Vocal_2 model probably is running on CUDA: 99% | 276/280 | 01:05<<00:00
MDX Kim_Vocal_2 model probably is running on CUDA: 99% | 277/280 | 01:05<<00:00
MDX Kim_Vocal_2 model probably is running on CUDA: 99% | 278/280 | 01:06<<00:00
MDX Kim_Vocal_2 model probably is running on CUDA: 100% | 279/280 | 01:06<<00:00
MDX Kim_Vocal_2 model probably is running on CUDA: 100% | 280/280 | 01:06<<00:00
MDX Kim_Vocal_2 model probably is running on CUDA: 100% | 280/280 | 01:07<<00:00
Starting transcription on: C:\Users\leo\AppData\Local\Temp\bk_asr\tmppif13f8k\audio.wav
1% | 29/4200 | 00:01<<03:27 | 20.08 audio seconds/s
2% | 69/4200 | 00:02<<02:30 | 27.51 audio seconds/s
2% | 99/4200 | 00:04<<02:46 | 24.57 audio seconds/s
3% | 129/4200 | 00:05<<02:52 | 23.64 audio seconds/s
4% | 162/4200 | 00:06<<02:47 | 24.16 audio seconds/s
5% | 200/4200 | 00:08<<02:41 | 24.79 audio seconds/s
6% | 233/4200 | 00:10<<02:55 | 22.54 audio seconds/s
6% | 265/4200 | 00:11<<02:54 | 22.49 audio seconds/s
7% | 295/4200 | 00:13<<03:02 | 21.40 audio seconds/s
8% | 321/4200 | 00:15<<03:07 | 20.66 audio seconds/s
8% | 353/4200 | 00:24<<04:24 | 14.52 audio seconds/s
9% | 375/4200 | 00:26<<04:25 | 14.39 audio seconds/s
10% | 403/4200 | 00:27<<04:23 | 14.40 audio seconds/s
10% | 433/4200 | 00:29<<04:18 | 14.55 audio seconds/s
11% | 462/4200 | 00:45<<06:08 | 10.15 audio seconds/s
12% | 489/4200 | 00:47<<05:58 | 10.36 audio seconds/s
12% | 521/4200 | 00:58<<06:55 | 8.85 audio seconds/s
13% | 546/4200 | 00:59<<06:40 | 9.13 audio seconds/s
14% | 574/4200 | 01:09<<07:18 | 8.27 audio seconds/s
14% | 605/4200 | 01:18<<07:46 | 7.71 audio seconds/s
15% | 632/4200 | 01:20<<07:32 | 7.89 audio seconds/s
16% | 660/4200 | 01:26<<07:42 | 7.65 audio seconds/s
16% | 692/4200 | 01:27<<07:25 | 7.87 audio seconds/s
17% | 720/4200 | 01:35<<07:40 | 7.56 audio seconds/s
18% | 748/4200 | 01:44<<08:02 | 7.15 audio seconds/s
19% | 778/4200 | 01:54<<08:22 | 6.81 audio seconds/s
19% | 803/4200 | 02:05<<08:50 | 6.40 audio seconds/s
20% | 825/4200 | 02:23<<09:47 | 5.74 audio seconds/s
20% | 855/4200 | 02:26<<09:31 | 5.85 audio seconds/s
21% | 884/4200 | 02:32<<09:33 | 5.79 audio seconds/s

@terryleo88 terryleo88 added the question Further information is requested label Jan 28, 2025
@philpw99
Copy link

那会不会是从视频的24秒开始有很多背景音乐或者吵杂人声?

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

No branches or pull requests

2 participants