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.

Sign up for GitHub

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

Jump to bottom

faster模式使用cuda报错 #737

Open
ZhiBeiYou-yxt opened this issue Feb 20, 2025 · 4 comments
Open

faster模式使用cuda报错 #737

ZhiBeiYou-yxt opened this issue Feb 20, 2025 · 4 comments

Comments

@ZhiBeiYou-yxt
Copy link

出错信息
使用faster-whisper在cuda下报错，提示“没有识别到任何说话声”。使用openai-whisper在cuda下不报错。两者使用cpu进行识别都不报错
Image

复现步骤

  1. 使用的哪个功能
    识别字幕并翻译
  2. faster模式/openai模式？
    faster模式报错，openai模式不报错
  3. 使用的模型名
    large-v3
    操作系统
  • Ubuntu

软件左上角版本号数字
v3.53
报错log

2025-02-20 08:58:03,414 - VideoTrans - INFO - start
2025-02-20 08:58:04,327 - VideoTrans - INFO - 开始处理
2025-02-20 08:58:04,341 - VideoTrans - INFO - self.cfg={'cache_folder': '/home/Software/VideoTrans/pyvideotrans-main/tmp/6bfac8a00a', 'target_dir': '/home//下载/_video_out/123', 'remove_noise': False, 'detect_language': 'ja', 'subtitle_language': None, 'source_language_code': 'ja', 'target_language_code': None, 'source_sub': '/home/下载/_video_out/123/ja.srt', 'target_sub': None, 'source_wav': '/home/Software/VideoTrans/pyvideotrans-main/tmp/6bfac8a00a/ja.m4a', 'source_wav_output': '/home/下载/_video_out/123/ja.m4a', 'target_wav': '', 'target_wav_output': '', 'novoice_mp4': '/home/Software/VideoTrans/pyvideotrans-main/tmp/6bfac8a00a/novoice.mp4', 'targetdir_mp4': '/home/下载/_video_out/123/123.mp4', 'instrument': None, 'vocal': None, 'shibie_audio': '/home/下载/_video_out/123/shibie.wav', 'background_music': None, 'app_mode': 'tiqu', 'subtitle_type': 0, 'append_video': False, 'only_video': False, 'volume': '0%', 'pitch': '0Hz', 'voice_rate': '+0%', 'translate_type': 1, 'source_language': '日语', 'target_language': '-', 'tts_type': 0, 'voice_role': 'No', 'recogn_type': 0, 'model_name': 'large-v3-turbo', 'split_type': 'all', 'voice_autorate': False, 'video_autorate': True, 'is_separate': False, 'cuda': True, 'back_audio': '', 'clear_cache': False, 'copysrt_rawvideo': False, 'subtitles': '', 'name': '/home/下载/123.m4a', 'dirname': '/home/下载', 'basename': '123.m4a', 'noextname': '123', 'ext': 'm4a', 'uuid': '6bfac8a00a'}
2025-02-20 08:58:04,343 - VideoTrans - INFO - forbid
2025-02-20 08:58:04,344 - VideoTrans - INFO - 开始处理
2025-02-20 08:58:04,824 - VideoTrans - INFO - force_cpu=False,cmd=['ffmpeg', '-hide_banner', '-ignore_unknown', '-y', '-i', '/home/下载/123.m4a', '-vn', '-ac', '1', '-b:a', '192k', '-c:a', 'aac', '/home/Software/VideoTrans/pyvideotrans-main/tmp/6bfac8a00a/ja.m4a']
2025-02-20 08:58:09,062 - VideoTrans - INFO - force_cpu=False,cmd=['ffmpeg', '-hide_banner', '-ignore_unknown', '-y', '-i', '/home/Software/VideoTrans/pyvideotrans-main/tmp/6bfac8a00a/ja.m4a', '-ac', '1', '-ar', '16000', '/home//下载/_video_out/123/shibie.wav']
2025-02-20 08:58:09,832 - VideoTrans - INFO - 开始进行语音识别
2025-02-20 08:58:20,710 - VideoTrans - INFO - large-v3-turbo Loaded
2025-02-20 08:58:23,765 - VideoTrans - ERROR - 没有识别到任何说话声
Traceback (most recent call last):
File "/home/Software/VideoTrans/pyvideotrans-main/videotrans/recognition/_base.py", line 73, in run
return self._exec()
File "/home/Software/VideoTrans/pyvideotrans-main/videotrans/recognition/_overall.py", line 138, in _exec
raise Exception(self.error)
Exception: 没有识别到任何说话声
2025-02-20 08:58:23,768 - VideoTrans - ERROR - 没有识别到任何说话声
2025-02-20 08:58:23,769 - VideoTrans - ERROR - 没有识别到任何说话声('没有识别到任何说话声',)
2025-02-20 08:58:23,837 - VideoTrans - ERROR - 没有识别到任何说话声
Traceback (most recent call last):
File "/home/Software/VideoTrans/pyvideotrans-main/videotrans/task/job.py", line 77, in run
trk.recogn()
File "/home/Software/VideoTrans/pyvideotrans-main/videotrans/task/trans_create.py", line 330, in recogn
raw_subtitles = run_recogn(
File "/home/Software/VideoTrans/pyvideotrans-main/videotrans/recognition/init.py", line 215, in run
return FasterAll(**kwargs).run()
File "/home/Software/VideoTrans/pyvideotrans-main/videotrans/recognition/_base.py", line 73, in run
return self._exec()
File "/home/Software/VideoTrans/pyvideotrans-main/videotrans/recognition/_overall.py", line 138, in _exec
raise Exception(self.error)
Exception: 没有识别到任何说话声
2025-02-20 08:58:23,838 - VideoTrans - ERROR - 语音识别阶段出错:没有识别到任何说话声
@elcerilla
Copy link

elcerilla commented Mar 6, 2025 •
edited
Loading

same problem, all drivers installed, cuda 124 , cudnnn , nvidia-smi works. dont know how solve

@jianchang512
Copy link
Owner

右上角 保存到 手动选个位置。再试试

@elcerilla
Copy link

ideo:244kB audio:35kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.171715%
[aac @ 0x58def8fc2340] Qavg: 3868.655
2025-03-06 12:46:16,016 - VideoTrans - ERROR - CUDA failed with error initialization error
Traceback (most recent call last):
File "/root/pyvideotrans/videotrans/recognition/_base.py", line 73, in run
return self._exec()
File "/root/pyvideotrans/videotrans/recognition/_overall.py", line 138, in _exec
raise Exception(self.error)
Exception: CUDA failed with error initialization error
2025-03-06 12:46:16,017 - VideoTrans - ERROR - CUDA failed with error initialization error
2025-03-06 12:46:16,017 - VideoTrans - ERROR - CUDA failed with error initialization error('CUDA failed with error initialization error',)
Error calling Python override of QThread::run(): 2025-03-06 12:46:16,032 - VideoTrans - ERROR - Uncaught exception
Traceback (most recent call last):
File "/root/pyvideotrans/videotrans/task/_only_one.py", line 34, in run
trk.recogn()
File "/root/pyvideotrans/videotrans/task/trans_create.py", line 331, in recogn
raw_subtitles = run_recogn(
File "/root/pyvideotrans/videotrans/recognition/init.py", line 228, in run
return FasterAll(**kwargs).run()
File "/root/pyvideotrans/videotrans/recognition/_base.py", line 73, in run
return self._exec()
File "/root/pyvideotrans/videotrans/recognition/_overall.py", line 138, in _exec
raise Exception(self.error)
Exception: CUDA failed with error initialization error
/root/pyvideotrans/models/models--Systran--faster-whisper-large-v3
res=True
2025-03-06 12:47:11,858 - VideoTrans - ERROR - CUDA failed with error initialization error
Traceback (most recent call last):
File "/root/pyvideotrans/videotrans/recognition/_base.py", line 73, in run
return self._exec()
File "/root/pyvideotrans/videotrans/recognition/_overall.py", line 138, in _exec
raise Exception(self.error)
Exception: CUDA failed with error initialization error
2025-03-06 12:47:11,858 - VideoTrans - ERROR - CUDA failed with error initialization error
2025-03-06 12:47:11,858 - VideoTrans - ERROR - CUDA failed with error initialization error('CUDA failed with error initialization error',)
Error calling Python override of QThread::run(): 2025-03-06 12:47:11,864 - VideoTrans - ERROR - Uncaught exception
Traceback (most recent call last):
File "/root/pyvideotrans/videotrans/task/_only_one.py", line 34, in run
trk.recogn()
File "/root/pyvideotrans/videotrans/task/trans_create.py", line 331, in recogn
raw_subtitles = run_recogn(
File "/root/pyvideotrans/videotrans/recognition/init.py", line 228, in run
return FasterAll(**kwargs).run()
File "/root/pyvideotrans/videotrans/recognition/_base.py", line 73, in run
return self._exec()
File "/root/pyvideotrans/videotrans/recognition/_overall.py", line 138, in _exec
raise Exception(self.error)
Exception: CUDA failed with error initialization error

(venv) root@pruebaD:~/pyvideotrans# nvidia-smi
Thu Mar 6 11:42:20 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.107.02 Driver Version: 550.107.02 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA RTX A5000 Off | 00000000:41:00.0 Off | Off |
| 30% 45C P8 20W / 230W | 10123MiB / 24564MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
+-----------------------------------------------------------------------------------------+
(venv) root@pruebaD:/pyvideotrans# nano test_cuda.py
[1]+ Killed python3 sp.py
(venv) root@pruebaD:/pyvideotrans# python3 test_cuda.py
True
NVIDIA RTX A5000

@jianchang512
Copy link
Owner

jianchang512 commented Mar 6, 2025 •
edited
Loading

pip3 install --reinstall-force pyside6

retry

update driver

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@jianchang512 @ZhiBeiYou-yxt @elcerilla