We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
===========任务开始=========== 时间:2025-01-30 21:42:21.746964 开始转录
===========转录任务开始=========== 时间:2025-01-30 21:42:21.749551 开始转换音频 转换为音频执行命令: ffmpeg -i C:\Users\wycbug\Desktop\youtube\LangChain\LangGraph_Python\LangGraph_-Human-in-the-Loop.mp4 -map 0:a -ac 1 -ar 16000 -af aresample=async=1 -y C:\Users\wycbug\AppData\Local\VideoCaptioner\work-dir\LangGraph-Human-in-the-Loop\【Audio】LangGraph-_Human-in-the-Loop.wav 开始语音转录 Faster Whisper 执行命令: faster-whisper-xxl.exe -m large-v3 --print_progress --model_dir C:\Users\wycbug\AppData\Local\VideoCaptioner\AppData\models C:\Users\wycbug\AppData\Local\Temp\bk_asr\tmp8rx1y1pc\audio.wav -l en -d cuda --output_format srt -o source --vad_filter true --vad_threshold 0.40 --vad_method silero_v4 --one_word 1 Standalone Faster-Whisper-XXL r194.5 running on: CUDA Note: 'large-v3' model may produce worse results than 'large-v2'! Starting transcription on: C:\Users\wycbug\AppData\Local\Temp\bk_asr\tmp8rx1y1pc\audio.wav 27% | 29/107 | 00:02<<00:06 | 12.00 audio seconds/s 55% | 59/107 | 00:17<<00:14 | 3.35 audio seconds/s 82% | 88/107 | 00:20<<00:04 | 4.34 audio seconds/s 99% | 106/107 | 00:22<<00:00 | 4.75 audio seconds/s 99% | 106/107 | 00:22<<00:00 | 4.75 audio seconds/s Transcription speed: 4.74 audio seconds/s Subtitles are written to 'C:\Users\wycbug\AppData\Local\Temp\bk_asr\tmp8rx1y1pc' directory. Operation finished in: 0:00:27.461 Faster Whisper 返回值: 3221226505 2025-01-30 21:42:58 - faster_whisper - ERROR - Faster Whisper 错误: 2025-01-30 21:42:58 - transcript_thread - ERROR - 转录过程中发生错误: Traceback (most recent call last): File "C:\Users\wycbug\AppData\Local\VideoCaptioner\app\core\thread\transcript_thread.py", line 130, in run asr_data = self.asr.run(callback=self.progress_callback) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\wycbug\AppData\Local\VideoCaptioner\app\core\bk_asr\BaseASR.py", line 73, in run resp_data = self._run(callback, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\wycbug\AppData\Local\VideoCaptioner\app\core\bk_asr\FasterWhisperASR.py", line 208, in _run raise RuntimeError(error_msg) RuntimeError 2025-01-30 21:42:58 - subtitle_pipeline_thread - ERROR - pipeline 发生错误: 转录过程中发生错误,终止流程
The text was updated successfully, but these errors were encountered:
用AI解释了一下日志,看起来是我设备问题。
根据提供的日志信息,我们可以看到转录过程中发生了错误,具体来说是在运行Faster Whisper时出现了问题。错误信息为RuntimeError,并且有一个返回值3221226505。
RuntimeError
3221226505
首先,我们需要了解这个返回值代表什么。3221226505是Windows系统中的一个错误代码,相当于0xC0000005,它通常表示“访问违规”(Access Violation)。这个错误可能是由于程序尝试访问一个无效的内存地址导致的。
0xC0000005
在这种情况下,错误发生在Faster Whisper的执行过程中。Faster Whisper是使用CUDA进行加速的,这意味着它可能与GPU资源相关的问题有关。
可能的原因包括:
为了排查这个问题,可以尝试以下步骤:
通过这些步骤,应该能够找到错误的原因并进行相应的修复。
Sorry, something went wrong.
不是啦,这又是那个典型的FasterWhisper 99%错误,是FasterWhisper结束运行时没有报告100%而导致的。 难道WEIFENG大神到现在还没有修复? 那在这之前,就先用着小弟改的吧 https://github.com/philpw99/VideoCaptioner/releases/tag/v1.2.0_2.0
No branches or pull requests
问题描述 | Problem Description
===========任务开始===========
时间:2025-01-30 21:42:21.746964
开始转录
===========转录任务开始===========
时间:2025-01-30 21:42:21.749551
开始转换音频
转换为音频执行命令: ffmpeg -i C:\Users\wycbug\Desktop\youtube\LangChain\LangGraph_Python\LangGraph_-Human-in-the-Loop.mp4 -map 0:a -ac 1 -ar 16000 -af aresample=async=1 -y C:\Users\wycbug\AppData\Local\VideoCaptioner\work-dir\LangGraph-Human-in-the-Loop\【Audio】LangGraph-_Human-in-the-Loop.wav
开始语音转录
Faster Whisper 执行命令: faster-whisper-xxl.exe -m large-v3 --print_progress --model_dir C:\Users\wycbug\AppData\Local\VideoCaptioner\AppData\models C:\Users\wycbug\AppData\Local\Temp\bk_asr\tmp8rx1y1pc\audio.wav -l en -d cuda --output_format srt -o source --vad_filter true --vad_threshold 0.40 --vad_method silero_v4 --one_word 1
Standalone Faster-Whisper-XXL r194.5 running on: CUDA
Note: 'large-v3' model may produce worse results than 'large-v2'!
Starting transcription on: C:\Users\wycbug\AppData\Local\Temp\bk_asr\tmp8rx1y1pc\audio.wav
27% | 29/107 | 00:02<<00:06 | 12.00 audio seconds/s
55% | 59/107 | 00:17<<00:14 | 3.35 audio seconds/s
82% | 88/107 | 00:20<<00:04 | 4.34 audio seconds/s
99% | 106/107 | 00:22<<00:00 | 4.75 audio seconds/s
99% | 106/107 | 00:22<<00:00 | 4.75 audio seconds/s
Transcription speed: 4.74 audio seconds/s
Subtitles are written to 'C:\Users\wycbug\AppData\Local\Temp\bk_asr\tmp8rx1y1pc' directory.
Operation finished in: 0:00:27.461
Faster Whisper 返回值: 3221226505
2025-01-30 21:42:58 - faster_whisper - ERROR - Faster Whisper 错误:
2025-01-30 21:42:58 - transcript_thread - ERROR - 转录过程中发生错误:
Traceback (most recent call last):
File "C:\Users\wycbug\AppData\Local\VideoCaptioner\app\core\thread\transcript_thread.py", line 130, in run
asr_data = self.asr.run(callback=self.progress_callback)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\wycbug\AppData\Local\VideoCaptioner\app\core\bk_asr\BaseASR.py", line 73, in run
resp_data = self._run(callback, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\wycbug\AppData\Local\VideoCaptioner\app\core\bk_asr\FasterWhisperASR.py", line 208, in _run
raise RuntimeError(error_msg)
RuntimeError
2025-01-30 21:42:58 - subtitle_pipeline_thread - ERROR - pipeline 发生错误:
转录过程中发生错误,终止流程
日志信息(可选)| Logs (Optional)
The text was updated successfully, but these errors were encountered: