#5228 TaskCfgVTT(uuid='affd11f808', name='D:/1_Dowload/0616(1).MP3', dirname='D:/1_Dowload', noextname='0616(1)', basename='06

36.229* Posted at: 1 day ago

下载模型失败,你可以打开以下网址,将所有文件下载到
E:/pyVideoTrans/win-pyvideotrans-v4.02-0615/models/models--Qwen--Qwen3-TTS-12Hz-1.7B-Base 文件夹内

[https://modelscope.cn/models/Qwen/Qwen3-TTS-12Hz-1.7B-Base/tree/main]
None: Max retries exceeded with url: https://www.modelscope.cn/api/v1/models/Qwen/Qwen3-TTS-12Hz-1.7B-Base/repo?Revision=master&FilePath=speech_tokenizer%2Fmodel.safetensors (Caused by ConnectionError(ReadTimeoutError("HTTPSConnectionPool(host='www.modelscope.cn', port=443): Read timed out.")))[faster-whisper(本地内置), Google(免费), Qwen3-TTS(本地内置)]
Traceback (most recent call last):
File "urllib3\response.py", line 779, in _error_catcher
File "urllib3\response.py", line 904, in _raw_read
File "urllib3\response.py", line 887, in _fp_read
File "http\client.py", line 466, in read
File "socket.py", line 717, in readinto
File "ssl.py", line 1307, in recv_into
File "ssl.py", line 1163, in read
TimeoutError: The read operation timed out

The above exception was the direct caus
......
download_file_lists(
File "videotrans\util\help_down.py", line 326, in _patched_dfl
File "modelscope\hub\snapshot_download.py", line 596, in _download_file_lists

_download_single_file(filtered_repo_files)

File "modelscope\utils\thread_utils.py", line 66, in wrapper

results.append(future.result())

File "concurrent\futures\_base.py", line 451, in result
File "concurrent\futures\_base.py", line 403, in __get_result
File "concurrent\futures\thread.py", line 58, in run
File "modelscope\hub\snapshot_download.py", line 582, in _download_single_file

download_file(

File "modelscope\hub\file_download.py", line 721, in download_file

url,

File "modelscope\hub\file_download.py", line 608, in http_get_model_file

retry.sleep()

File "urllib3\util\retry.py", line 519, in increment
urllib3.exceptions.MaxRetryError: None: Max retries exceeded with url: https://www.modelscope.cn/api/v1/models/Qwen/Qwen3-TTS-12Hz-1.7B-Base/repo?Revision=master&FilePath=speech_tokenizer%2Fmodel.safetensors (Caused by ConnectionError(ReadTimeoutError("HTTPSConnectionPool(host='www.modelscope.cn', port=443): Read timed out.")))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 87, in run
File "videotrans\task\trans_create.py", line 679, in dubbing
File "videotrans\task\trans_create.py", line 1001, in _tts
File "videotrans\tts\__init__.py", line 184, in run
File "videotrans\tts\_base.py", line 77, in run
File "videotrans\tts\_qwenttslocal.py", line 27, in _download
File "videotrans\util\help_down.py", line 378, in check_and_down_ms
videotrans.configure.excepts.DownloadModelsError: 下载模型失败,你可以打开以下网址,将所有文件下载到
E:/pyVideoTrans/win-pyvideotrans-v4.02-0615/models/models--Qwen--Qwen3-TTS-12Hz-1.7B-Base 文件夹内

[https://modelscope.cn/models/Qwen/Qwen3-TTS-12Hz-1.7B-Base/tree/main]
None: Max retries exceeded with url: https://www.modelscope.cn/api/v1/models/Qwen/Qwen3-TTS-12Hz-1.7B-Base/repo?Revision=master&FilePath=speech_tokenizer%2Fmodel.safetensors (Caused by ConnectionError(ReadTimeoutError("HTTPSConnectionPool(host='www.modelscope.cn', port=443): Read timed out.")))
TaskCfgVTT(uuid='affd11f808', name='D:/1_Dowload/0616(1).MP3', dirname='D:/1_Dowload', noextname='0616(1)', basename='0616(1).MP3', ext='mp3', target_dir='0616(1)-mp3', cache_folder='E:/pyVideoTrans/win-pyvideotrans-v4.02-0615/tmp/40688/affd11f808', is_cuda=True, source_language='英语', source_language_code='en', source_sub='0616(1)-mp3/en.srt', source_wav='E:/pyVideoTrans/win-pyvideotrans-v4.02-0615/tmp/40688/affd11f808/en.wav', source_wav_output='0616(1)-mp3/en.m4a', target_language='繁体中文', target_language_code='zh-tw', target_sub='0616(1)-mp3/zh-tw.srt', target_wav='E:/pyVideoTrans/win-pyvideotrans-v4.02-0615/tmp/40688/affd11f808/target.wav', target_wav_output='0616(1)-mp3/zh-tw.m4a', translate_type=0, tts_type=1, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='clone', voice_autorate=True, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='en', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=0, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='0616(1)-mp3/0616(1).mp4', novoice_mp4='E:/pyVideoTrans/win-pyvideotrans-v4.02-0615/tmp/40688/affd11f808/novoice.mp4', is_separate=False, embed_bgm=True, instrument='E:/pyVideoTrans/win-pyvideotrans-v4.02-0615/tmp/40688/affd11f808/instrument.wav', vocal='E:/pyVideoTrans/win-pyvideotrans-v4.02-0615/tmp/40688/affd11f808/vocal.wav', clear_cache=True, background_music='', subtitle_type=1, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8)


=
system:Windows-10-10.0.26200-SP0
version:v4.02
frozen:True
language:zh
root_dir:E:/pyVideoTrans/win-pyvideotrans-v4.02-0615

1 Replies

模型下载失败的根本原因是网络连接 modelscope.cn 超时,导致 Qwen3-TTS 本地模型文件无法自动下载。

解决方案:

  1. 手动下载模型:打开浏览器访问 https://modelscope.cn/models/Qwen/Qwen3-TTS-12Hz-1.7B-Base/tree/main,将该页面内的所有文件(.json.bin.txt 等)下载到本地,并复制到日志中提示的文件夹:
    E:/pyVideoTrans/win-pyvideotrans-v4.02-0615/models/models--Qwen--Qwen3-TTS-12Hz-1.7B-Base
    覆盖已存在的文件即可。完成后重新执行任务。
  2. 更换下载源:如果 modelscope 持续超时,可改用 Hugging Face 镜像。模型在 Hugging Face 的地址为 https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base/tree/main。将全部文件下载到上述同一文件夹即可。
  3. 临时绕过:若需立即使用,可在主界面“配音渠道”中暂时切换为 Edge-TTS(免费在线,无需下载模型),等后续网络稳定后再换回本地 Qwen3-TTS。
  4. 检查网络环境:国内访问 modelscope 一般不需要代理,但若仍超时,可尝试在软件主界面第5行填写代理地址(如 http://127.0.0.1:7890),或使用 VPN。

如果手动下载后仍报错,请提供 logs/ 目录下的最新日志文件(复制约底部30行)以便进一步分析。

Post Your Reply
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: ko-fi.com/jianchang512

Related resource