#7261 语音识别阶段出错:[faster-whisper(本地)] 多次重试连接失败,服务可能暂时不可用:Traceback (most recent call last):

118.167**6 Posted at: 1 hour ago

语音识别阶段出错:[faster-whisper(本地)] 多次重试连接失败,服务可能暂时不可用:
Traceback (most recent call last):
File "videotrans\task\job.py", line 113, in run
File "videotrans\task\trans_create.py", line 360, in recogn
File "videotrans\recognition\__init__.py", line 243, in run
File "videotrans\recognition\_base.py", line 78, in run
File "videotrans\recognition\_overall.py", line 182, in _exec
RuntimeError: urllib3.exceptions.SSLError: EOF occurred in violation of protocol (_ssl.c:997)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "requests\adapters.py", line 644, in send
File "urllib3\connectionpool.py", line 841, in urlopen
File "urllib3\util\retry.py", line 519, in increment
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/mobiuslabsgmbh/faster-whisper-large-v3-turbo/revision/main (Caused by SSLError(SSLEOFError(8, 'EOF occurred in v
......
adapters.py", line 675, in send
requests.exceptions.SSLError: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/mobiuslabsgmbh/faster-whisper-large-v3-turbo/revision/main (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:997)')))"), '(Request ID: 1efb01bc-e0e9-4467-a93b-d8387edf9730)')

TaskCfg(cache_folder='D:/tts/tmp/752/af1eec1dc0', target_dir='C:/Users/97685/Desktop/素材/音频/_video_out/acv_2-wav', remove_noise=False, is_separate=False, detect_language='de', subtitle_language=None, source_language='德语', target_language='简体中文', source_language_code='de', target_language_code='zh-cn', source_sub='C:/Users/97685/Desktop/素材/音频/_video_out/acv_2-wav/de.srt', target_sub='C:/Users/97685/Desktop/素材/音频/_video_out/acv_2-wav/zh-cn.srt', source_wav='D:/tts/tmp/752/af1eec1dc0/de.wav', source_wav_output='C:/Users/97685/Desktop/素材/音频/_video_out/acv_2-wav/de.m4a', target_wav='D:/tts/tmp/752/af1eec1dc0/target.wav', target_wav_output='C:/Users/97685/Desktop/素材/音频/_video_out/acv_2-wav/zh-cn.m4a', subtitles='', novoice_mp4='D:/tts/tmp/752/af1eec1dc0/novoice.mp4', noextname='acv_2', shibie_audio=None, targetdir_mp4='C:/Users/97685/Desktop/素材/音频/_video_out/acv_2-wav/acv_2.mp4', instrument=None, vocal=None, back_audio='', background_music=None, app_mode='tiqu', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', copysrt_rawvideo=False, clear_cache=False, translate_type=1, tts_type=0, recogn_type=0, model_name='large-v3-turbo', split_type=0, voice_autorate=False, video_autorate=False, cuda=True, name='C:/Users/97685/Desktop/素材/音频/acv_2.wav', basename='acv_2.wav', ext='wav', dirname='C:/Users/97685/Desktop/素材/音频', shound_del_name=None, uuid='af1eec1dc0', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=False)


=
system:Windows-10-10.0.26200-SP0
version:v3.89
frozen:True
language:zh
root_dir:D:/tts

1 Replies

#1 DeepSeek reply at 1 hour ago

核心原因是模型下载失败:软件需要从 huggingface.co 下载 large-v3-turbo 模型,但该域名在国内被屏蔽,导致 SSL 连接中断(EOF occurred in violation of protocol)。此报错与语音识别本身无关,纯粹是网络问题。

解决方案(任选其一):

  1. 配置代理后重试:在软件主界面「对齐控制」行右侧的网络代理文本框中填写可用的代理地址(如 http://127.0.0.1:10808),确保代理服务已开启且端口正确,然后重新执行任务。
  2. 手动下载模型(推荐,最稳妥):

  3. 改用更小的模型:先换用 smallmedium 模型测试(但同样需要下载,若网络不通仍会失败)。
  4. 改用在线识别渠道:如 OpenAI 语音识别API、Gemini 等,但这些渠道同样需要能访问外网。

另外,你的版本为 v3.89,与当前最新版本差距较大,建议升级到最新版本 v4.12 以获得更好的兼容性。

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