#8192 语音识别阶段出错[Qwen-ASR(内置)] list index out of range:Traceback (most recent call last): File

240e**99c1 Posted at: 1 hour ago

语音识别阶段出错[Qwen-ASR(内置)] list index out of range:Traceback (most recent call last):
File "videotrans\process\stt_qwen.py", line 110, in qwen3asr_fun
IndexError: list index out of range

Traceback (most recent call last):

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

File "videotrans\task\job.py", line 101, in process_task

File "videotrans\task\speech2text.py", line 97, in recogn

File "videotrans\recognition\__init__.py", line 141, in run

File "videotrans\recognition\_base.py", line 101, in run

File "videotrans\recognition\_qwenasrlocal.py", line 84, in _exec

File "videotrans\configure\base.py", line 277, in _new_process

videotrans.configure.excepts.VideoTransError: list index out of range:Traceback (most recent call last):
File "videotrans\process\stt_qwen.py", line 110, in qwen3asr_fun
IndexError: list index out of range
trk=[SpeechToText]: uuid='3c8973de11', proxy_str='http://127.0.0.1:7897', cfg=[TaskCfgSTT]
原始输入文件名: D:/已经下载博主、/UID1045008845906698_肖胰有道_发布作品/2024-11-20 18.46.19-视频-肖胰有道-世界胰腺癌日来临之际的义诊,希望...附院胰腺中心 #义诊 #世界胰腺癌日.mp4,
输出结果保存到文件夹: D:/fanyi/output/recogn,
临时文件夹: D:/fanyi/tmp/17984/3c8973de11
已启用CUDA加速
已选 降噪
已选 恢复标点符号
语音识别:Qwen-ASR(内置), 1.7B
发音语言:zh
已选 降噪
代理地址:http://127.0.0.1:7897, precent=1, hasend=False, should_recogn=True, should_trans=False, should_dubbing=False, should_hebing=False, out_format='srt', copysrt_rawvideo=True, spk_insert=False


=
system:Windows-10-10.0.26200-SP0
version:v4.16
frozen:True
language:zh_CN
root_dir:D:/fanyi

1 Replies

#1 DeepSeek reply at 1 hour ago

该错误是 Qwen-ASR 内置渠道在处理识别结果时发生内部下标越界(IndexError: list index out of range),通常不是由音频文件本身导致,而更可能是 Qwen-ASR 模型文件不完整/版本不匹配、或当前音频经降噪/标点恢复后送入模型时出现异常。

请按以下顺序排查:

  1. 确认软件为最新版:当前版本应不低于 v4.16。若低于,请下载最新完整包或补丁包覆盖。
  2. 检查 Qwen-ASR 模型目录是否完整:

    • v4.12 起 Qwen-ASR 必须使用 -hf 结尾的 transformers 版本模型,旧模型不通用。
    • 若选择的是 1.7B,请检查 软件目录/models/models--Qwen--Qwen3-ASR-1.7B-hf 目录是否完整;若为 0.6B,则检查 models--Qwen--Qwen3-ASR-0.6B-hf。
    • 模型下载不完整或残留旧文件会导致该报错。建议删除对应模型目录后重新下载。
  3. 临时关闭干扰项测试:在“设置更多参数”中暂时取消勾选“降噪”和“恢复标点符号”,再重新运行一次,排除音频预处理链路问题。
  4. 尝试更换识别渠道:如果问题依旧,可在语音识别渠道中改用 faster-whisper(内置),该渠道更稳定。
  5. 如果以上步骤仍无法解决,请提供 软件目录/logs/ 下最新日志文件底部约 30 行内容,以便进一步定位。

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