#4753 File model.bin is incomplete: failed to read a buffer of size 13107200 at position 590811106,Traceback (most recent call

128.241* Posted at: 13 hours ago

File model.bin is incomplete: failed to read a buffer of size 13107200 at position 590811106,Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 208, in faster_whisper
File "videotrans\process\stt_fun.py", line 173, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: File model.bin is incomplete: failed to read a buffer of size 13107200 at position 590811106

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 47, in run
File "videotrans\task\trans_create.py", line 320, in recogn
File "videotrans\recognition\__init__.py", line 188, in run
File "videotrans\recognition\_base.py", line 93, in run
File "videotrans\recognition\_whisper.py", line 35, in _exec
File "videotrans\recognition\_whisper.py", line 108, in _faster
File "videotrans\configure\base.py", line 240, in _new_process
videotrans.configure.excepts.VideoTransError: File model.bin is incomplete: failed to read a buffer of size 13107200 at position 590811106,Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 208, in faster_whisper
File "videotrans\process\stt_fun.py", line 173, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: File model.bin is incomplete: failed to read a buffer of size 13107200 at position 590811106
TaskCfgVTT(uuid='adb8264a04', name='E:/video/steel.mp4', dirname='E:/video', noextname='steel', basename='steel.mp4', ext='mp4', target_dir='E:/video/steel-mp4', cache_folder='E:/pyVideoTrans/pyvideotrans/tmp/7632/adb8264a04', is_cuda=False, source_language='简体中文', source_language_code='zh-cn', source_sub='E:/video/steel-mp4/zh-cn.srt', source_wav='E:/pyVideoTrans/pyvideotrans/tmp/7632/adb8264a04/zh-cn.wav', source_wav_output='E:/video/steel-mp4/zh-cn.m4a', target_language='英语', target_language_code='en', target_sub='E:/video/steel-mp4/en.srt', target_wav='E:/pyVideoTrans/pyvideotrans/tmp/7632/adb8264a04/target.wav', target_wav_output='E:/video/steel-mp4/en.m4a', translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Steffan(Male/US)', voice_autorate=True, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='zh-cn', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='E:/video/steel-mp4/steel.mp4', novoice_mp4='E:/pyVideoTrans/pyvideotrans/tmp/7632/adb8264a04/novoice.mp4', is_separate=False, embed_bgm=True, instrument=None, vocal='E:/pyVideoTrans/pyvideotrans/tmp/7632/adb8264a04/vocal.wav', clear_cache=False, background_music='', subtitle_type=1, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8)

3 Replies

Floor #1 DeepSeek reply at 13 hours ago

这是由于模型文件 model.bin 损坏或不完整导致的。常见原因是下载中途中断、网络不稳定或文件被截断。

解决方案：

删除损坏的模型文件：
进入软件安装目录下的 models/ 文件夹，找到 models--Systran--faster-whisper-large-v3-turbo 之类的子文件夹，删除其中所有的文件（或整个文件夹）。
重新下载模型：
重新启动软件，再次进行视频翻译。软件会在首次运行 ASR 时自动从 HuggingFace 重新下载完整模型。请确保网络稳定，若国内网络受限，可参考下方文档手动下载并放置模型。
备用方法（手动下载）：
访问 HuggingFace 模型仓库 Systran/faster-whisper-large-v3-turbo，手动下载全部文件，放入 models/models--Systran--faster-whisper-large-v3-turbo/ 目录中。

请查阅相关文档：

Floor #2 128.241* reply at 12 hours ago

mkl_malloc: failed to allocate memory:Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 303, in faster_whisper
File "faster_whisper\transcribe.py", line 1851, in restore_spsk

File "faster_whisper\transcribe.py", line 1190, in genesk

File "faster_whisper\transcribe.py", line 1400, in encode
RuntimeError: mkl_malloc: failed to allocate memory

Floor #3 DeepSeek reply at 12 hours ago

这是由于系统内存（RAM）或 GPU 显存不足导致的 mkl_malloc 分配失败。常见于使用 large-v3 等大模型且同时运行其他高内存任务时。请按以下顺序尝试解决：

关闭其他占用内存/显存的程序（如浏览器、视频编辑器、其他AI服务）。
缩小 ASR 模型：在主界面将语音识别模型从 large-v3-turbo 切换为 medium 或 small。
降低内存/显存占用（推荐）：
- 打开 菜单 → 工具 → 高级选项 → 语音识别参数。
- 将 CUDA数据类型 设为 int8（若未启用CUDA则忽略此项）。
- 将 beam_size 和 best_of 均设为 1。
- 勾选 Whisper预分割音频?，可大幅降低单次内存占用。
若仍失败：检查系统物理内存是否小于 16GB，建议增加虚拟内存或升级硬件。

请查阅相关文档：