#7816 语音识别阶段出错[faster-whisper(内置)] [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Co

2409**ed93 Posted at: 3 hours ago

语音识别阶段出错[faster-whisper(内置)] [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Conv node. Name:'/encoder/feature_extractor/Conv' Status Message: bad allocation:Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 108, in faster_whisper
File "faster_whisper\transcribe.py", line 890, in transcribe
File "faster_whisper\vad.py", line 89, in get_speech_timestamps
File "faster_whisper\vad.py", line 343, in call
File "onnxruntime\capi\onnxruntime_inference_collection.py", line 287, in run

self._validate_input(list(input_dict_ort_values.keys()))

onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Conv node. Name:'/encoder/feature_extractor/Conv' Status Message: bad allocation

Traceback (most recent call last):

File "videotrans\task\job.py", line 35, in run

File "videotrans\task\job.py", line 1
......
File "videotrans\recognition\_base.py", line 99, in run

File "videotrans\recognition\_whisper.py", line 41, in _exec

File "videotrans\recognition\_whisper.py", line 138, in _faster

File "videotrans\configure\base.py", line 264, in _new_process

videotrans.configure.excepts.VideoTransError: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Conv node. Name:'/encoder/feature_extractor/Conv' Status Message: bad allocation:Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 108, in faster_whisper
File "faster_whisper\transcribe.py", line 890, in transcribe
File "faster_whisper\vad.py", line 89, in get_speech_timestamps
File "faster_whisper\vad.py", line 343, in call
File "onnxruntime\capi\onnxruntime_inference_collection.py", line 287, in run

self._validate_input(list(input_dict_ort_values.keys()))

onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Conv node. Name:'/encoder/feature_extractor/Conv' Status Message: bad allocation

self.cfg=[TaskCfgVTT]当前工作模式: 转录并翻译字幕
原始输入文件名: E:/活宝三人组190全/音频/052.Boobs_in_Arms.a.mp4,
输出结果保存到文件夹: E:/活宝三人组190全/字幕/052.Boobs_in_Arms.a-mp4,
临时文件夹: E:/BaiduNetdiskDownload/win-pyvideotrans-v4.13/tmp/17924/03598b417b
未选 清理已存在
已启用CUDA加速
未选 降噪
语音识别:faster-whisper(内置), large-v3-turbo, 发音语言: 英语, 断句方式:默认断句
翻译渠道:字节大模型,原始语言:英语,目标语言:简体中文, 已选 发送完整字幕
输出字幕格式: 单字幕
代理地址:http://127.0.0.1:12334


=
system:Windows-10-10.0.26200-SP0
version:v4.13
frozen:True
language:zh_CN
root_dir:E:/BaiduNetdiskDownload/win-pyvideotrans-v4.13

1 Replies

#1 DeepSeek reply at 3 hours ago

bad allocation 表示内存分配失败。这是 VAD 阶段(vad.py)在 ONNX 运行 Conv 节点时,因内存不足导致的崩溃,与 CUDA 加速无直接关系,VAD 是固定使用 CPU/ONNX 运行的。

另外从日志看,您的视频信息中 width: 0, height: 0、video_streams: 0,这是纯音频 mp4,缺少视频流。此异常元数据也可能引发预处理阶段的资源分配异常,建议一并排查。

请按以下步骤处理:

  1. 释放内存:

    • 关闭其他占用内存的程序(浏览器、其他大模型任务等)。
    • 若同时批量处理多个视频,请减少并发,或改用 菜单-工具-高级选项-通用设置-批量翻译视频时每批数量 设为 1。
  2. 降低模型与精度:

    • 将 faster-whisper 模型由 large-v3-turbo 降为 medium 或 small。
    • 进入 菜单-工具-高级选项-语音识别参数,将 计算数据类型 改为 int8。
  3. 暂时避开 VAD 崩溃点:

    • 该报错发生在 faster_whisper/vad.py,可在 高级选项-语音识别参数 中将 选择VAD 切换为其他实现(如 silero 之外的可选项),或适当提高 语音阈值,减少送入 VAD 的数据。
    • 若视频有背景噪声,可先在主界面勾选 设置更多参数-降噪 预处理。
  4. 清理临时文件:

    • 清空软件根目录下 tmp/ 文件夹,因旧缓存可能损坏或占用空间。
  5. 确认文件本身正常:

    • 用播放器打开 052.Boobs_in_Arms.a.mp4 确认可正常播放、有声音轨;如该文件是分离出的纯音频,建议优先用 语音转录 独立功能处理,而非视频翻译。
  6. 若仍报错:

    • 更换为 openai-whisper(内置) 渠道,或改用在线识别渠道测试,以确认是否为本机内存问题。

如以上操作后仍失败,请提供软件根目录 logs/ 下最新日志文件底部约 30 行信息,以及本机内存(RAM)大小,以便进一步判断。

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource