MoneyPrinterTurbo
MoneyPrinterTurbo copied to clipboard
harry0703
语音生成mp3格式会被损坏
报错：## generating subtitle, provider: edge
2024-03-30 20:50:21 | WARNING | "./app\services\voice.py:1089": create_subtitle - failed, sub_items len: 0, script_lines len: 49
2024-03-30 20:50:21 | WARNING | "./app\services\task.py:87": start - subtitle file not found, fallback to whisper
2024-03-30 20:50:21 | INFO | "./app\services\subtitle.py:25": create - start, output file: .\storage\tasks\f93a4686-28a2-4842-95b5-16dc13e9d8b4\subtitle.srt
Format mp3 detected only with low score of 1, misdetection possible!
Failed to read frame size: Could not seek to 1026.
2024-03-30 20:50:21.594 Uncaught app exception
Traceback (most recent call last):
File "E:\AIstudy\conda\envs\MoneyPrinterTurbo\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 542, in _run_script
exec(code, module.dict)
File "E:\AIstudy\code\MoneyPrinterTurbo\webui\Main.py", line 376, in
音频文件应该是生成失败了，看看是否有错误日志？ 音频生成服务，需要访问网络，有时候需要VPN才能访问 确保网络通畅，再试试看 logs文件夹下的日志是空白的，当我使用vpn的时候ping油管的域名能ping通，但是依旧报错，似乎是url无法正确的被处理
我用VPN也是报这个错误，可以调openai接口生成文案，说明VPN是没问题的
## generating subtitle, provider: edge
2024-04-02 13:49:29 | WARNING | "./app/services/voice.py:1089": create_subtitle - failed, sub_items len: 0, script_lines len: 11
2024-04-02 13:49:29 | WARNING | "./app/services/task.py:98": start - subtitle file not found, fallback to whisper
2024-04-02 13:49:29 | INFO | "./app/services/subtitle.py:20": create - loading model: large-v3, device: CPU, compute_type: int8
2024-04-02 13:49:34 | INFO | "./app/services/subtitle.py:25": create - start, output file: ./storage/tasks/18921788-bb9d-402a-84f3-42f388caa0a6/subtitle.srt
Format mp3 detected only with low score of 1, misdetection possible!
Failed to read frame size: Could not seek to 1026.
2024-04-02 13:49:34.587 Uncaught app exception
Traceback (most recent call last):
File "miniconda3/envs/video/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 542, in _run_script
exec(code, module.__dict__)
File "MoneyPrinterTurbo/webui/Main.py", line 376, in <module>
tm.start(task_id=task_id, params=params)
File "MoneyPrinterTurbo/app/services/task.py", line 106, in start
subtitle.create(audio_file=audio_file, subtitle_file=subtitle_path)
File "MoneyPrinterTurbo/app/services/subtitle.py", line 29, in create
segments, info = model.transcribe(
^^^^^^^^^^^^^^^^^
File "miniconda3/envs/video/lib/python3.11/site-packages/faster_whisper/transcribe.py", line 294, in transcribe
audio = decode_audio(audio, sampling_rate=sampling_rate)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "miniconda3/envs/video/lib/python3.11/site-packages/faster_whisper/audio.py", line 46, in decode_audio
with av.open(input_file, mode="r", metadata_errors="ignore") as container:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "av/container/core.pyx", line 401, in av.container.core.open
File "av/container/core.pyx", line 265, in av.container.core.Container.__cinit__
File "av/container/core.pyx", line 285, in av.container.core.Container.err_check
File "av/error.pyx", line 336, in av.error.err_check
av.error.ValueError: [Errno 22] Invalid argument: 'MoneyPrinterTurbo/storage/tasks/18921788-bb9d-402a-84f3-42f388caa0a6/audio.mp3'; last error log: [mp3] Failed to read frame size: Could not seek to 1026.
音频文件应该是生成失败了，看看是否有错误日志？ 音频生成服务，需要访问网络，有时候需要VPN才能访问确保网络通畅，再试试看 logs文件夹下的是空白的，当我使用vpn时的时候ping油管的域名能ping通，但是仍然报错，似乎是url无法正确的被处理
把朗读声音的配音选择汉语选项，默认的不是汉语的，配音也生成不了汉语，所以会报错
音频文件应该是生成失败了，看看是否有错误日志？ 音频生成服务，需要访问网络，有时候需要VPN才能访问确保网络通畅，再试试看 logs文件夹下的是空白的，当我使用vpn时的时候ping油管的域名能ping通，但是仍然报错，似乎是url无法正确的被处理
把朗读声音的配音选择汉语选项，默认的不是汉语的，配音也生成不了汉语，所以会报错
我尝试了一下，问题解决了，感谢