#8828 语音识别阶段出错[faster-whisper(内置)] Unable to open file 'model.bin' in model 'D:/fanyiruanjian/win-pyvideotrans-v4.18/models/mo

149.119**5 Posted at: 8 hours ago

语音识别阶段出错[faster-whisper(内置)] Unable to open file 'model.bin' in model 'D:/fanyiruanjian/win-pyvideotrans-v4.18/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 84, in faster_whisper
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'D:/fanyiruanjian/win-pyvideotrans-v4.18/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 84, in run
File "videotrans\task\_stage_recogn.py", line 64, in recogn
File "videotrans\recognition\__init__.py", line 148, in run
File "videotrans\recognition\_base.py", line 101, in run
File "videotrans\recognition\_whisper.py", line 39, in _exec
File "videotrans\recognition\_whisper.py", line 136, in _faster
File "videotrans\configure\base.py", line 291, in _new_process
videotrans.configure.excepts.VideoTransError: Unable to open file 'model.bin' in model 'D:/fanyiruanjian/win-pyvideotrans-v4.18/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo',Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 84, in faster_whisper
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: Unable to open file 'model.bin' in model 'D:/fanyiruanjian/win-pyvideotrans-v4.18/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo'

trk=翻译视频 单视频模式
选择音视频文件: C:/Users/14995/Desktop/tiktok视频/中文视频/1a60acf375988b280f9f108540c15831.mp4,
输出目录: C:/Users/14995/Desktop/tiktok视频/英文视频/1a60acf375988b280f9f108540c15831-mp4,
self.cfg.cache_folder='D:/fanyiruanjian/win-pyvideotrans-v4.18/tmp/12692/d43584632a'
已选 清理已生成, 未选 CUDA加速
语音识别:faster-whisper(内置), large-v3-turbo, 发音语言: 简体中文
最长语音持续(秒): 5s
最短语音持续(毫秒): 3000ms
静音分割持续毫秒: 600ms
语音阈值: 0.45
选择VAD: silero
计算数据类型:default
识别准确度beam_size:5
识别准确度best_of:5
启用上下文感知:False
重复惩罚:1.0
文本压缩率:2.4
翻译渠道:Google(免费),发音语言:简体中文,目标语言:英语
传统翻译渠道每批字幕行数: 5
配音渠道:Edge-TTS(免费), 配音角色:Natasha(Female/AU), 目标语言:英语
Volume:+0%, Speed:+0%, 已选 配音加速, 已选 视频慢速
已选 移除每条字幕配音开头结尾静音缓冲
静音移除力度: default
已选: 二次语音识别, 二次识别所用模型: large-v3-turbo
二次识别最长语音持续(秒): 1.0s
二次识别最短语音持续(毫秒): 300ms
嵌入软字幕
已选 仅输出mp4
video duration:45366ms
video information:{'video_fps': 30.0, 'r_frame_rate': 30.0, 'video_codec_name': 'hevc', 'audio_codec_name': 'aac', 'width': 720, 'height': 1280, 'time': 45366, 'streams_len': 2, 'streams_audio': 1, 'video_streams': 1, 'color': 'yuv420p'}
self.cfg=TaskCfgVTT(uuid='d43584632a', name='C:/Users/14995/Desktop/tiktok视频/中文视频/1a60acf375988b280f9f108540c15831.mp4', dirname='C:/Users/14995/Desktop/tiktok视频/中文视频', noextname='1a60acf375988b280f9f108540c15831', basename='1a60acf375988b280f9f108540c15831.mp4', ext='mp4', target_dir='C:/Users/14995/Desktop/tiktok视频/英文视频/1a60acf375988b280f9f108540c15831-mp4', cache_folder='D:/fanyiruanjian/win-pyvideotrans-v4.18/tmp/12692/d43584632a', is_cuda=False, source_language='简体中文', source_language_code='zh-cn', source_sub='C:/Users/14995/Desktop/tiktok视频/英文视频/1a60acf375988b280f9f108540c15831-mp4/zh-cn.srt', source_wav='D:/fanyiruanjian/win-pyvideotrans-v4.18/tmp/12692/d43584632a/zh-cn.wav', source_wav_output='C:/Users/14995/Desktop/tiktok视频/英文视频/1a60acf375988b280f9f108540c15831-mp4/zh-cn.m4a', target_language='英语', target_language_code='en', target_sub='C:/Users/14995/Desktop/tiktok视频/英文视频/1a60acf375988b280f9f108540c15831-mp4/en.srt', target_wav='D:/fanyiruanjian/win-pyvideotrans-v4.18/tmp/12692/d43584632a/target.wav', target_wav_output='C:/Users/14995/Desktop/tiktok视频/英文视频/1a60acf375988b280f9f108540c15831-mp4/en.m4a', translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Natasha(Female/AU)', voice_autorate=True, video_autorate=True, remove_silent_mid=False, align_sub_audio=True, detect_language='zh', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=False, fix_punc=0, app_mode='biaozhun', subtitle_language=None, targetdir_mp4='C:/Users/14995/Desktop/tiktok视频/英文视频/1a60acf375988b280f9f108540c15831-mp4/1a60acf375988b280f9f108540c15831.mp4', novoice_mp4='D:/fanyiruanjian/win-pyvideotrans-v4.18/tmp/12692/d43584632a/novoice.mp4', is_separate=False, embed_bgm=True, instrument='D:/fanyiruanjian/win-pyvideotrans-v4.18/tmp/12692/d43584632a/instrument.wav', vocal='D:/fanyiruanjian/win-pyvideotrans-v4.18/tmp/12692/d43584632a/vocal.wav', clear_cache=True, background_music='', subtitle_type=2, only_out_mp4=True, recogn2pass=True, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8, batch=False)
video_duration_ms=45366


=
system:Windows-10-10.0.26200-SP0
version:v4.18
frozen:True
language:zh_CN
root_dir:D:/fanyiruanjian/win-pyvideotrans-v4.18

1 Replies

#1 DeepSeek reply at 8 hours ago

这是 faster-whisper 的 large-v3-turbo 模型文件没有下载完整(缺少核心的 model.bin),并非软件本身故障——模型首次使用需在线下载约 1.6GB 的文件,国内网络下载 huggingface 时经常中途失败或只下载了部分文件。

解决方案(任选其一)

方案一:手动补全模型文件(推荐,最稳)

  1. 打开 D:/fanyiruanjian/win-pyvideotrans-v4.18/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo 文件夹,先清空里面已下载的残缺文件。
  2. 用浏览器打开模型页面:https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main(国内打不开可换镜像 https://hf-mirror.com/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main)。
  3. 下载该页面所有文件(含 model.bin、config.json、tokenizer.json、vocabulary.txt、preprocessor_config.json 等),全部放入上述文件夹内,文件名保持不变(浏览器可能自动加 (1) 后缀,必须改回原名)。
  4. 回到软件重新执行。

方案二:换一个已缓存或更小的模型

在主界面把语音识别模型从 large-v3-turbo 改为 small 或 base,先跑通流程,之后有稳定网络再换回大模型。

方案三:确保网络可下载

开代理(建议全局模式)后,勾选主界面 清理已生成 重新执行,让软件重新下载模型;下载过程中不要关闭软件或断网。若仍失败,回到方案一手动下载。

补充提醒

  • 你的视频编码为 hevc,本次与报错无关,但若后续想无损输出需注意原始编码须为 H.264。
  • 报错信息里 Unable open/no such file 这类问题绝大多数源于模型下载不完整,其它模型(Qwen-ASR、F5-TTS 等)首次使用也同理。

请查阅相关文档:

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