#5188 TaskCfgVTT(uuid='dc9b8c47a1', name='C:/Users/Administrator/Downloads/Study_30min_DataCollection_2026-04-19_Joseph_1080p.

103.151* Posted at: 9 hours ago

list index out of range[阿里百炼 Qwen3-ASR, DeepSeek, Edge-TTS(免费)]
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 47, in run
File "videotrans\task\trans_create.py", line 322, in recogn
File "videotrans\recognition\__init__.py", line 190, in run
File "", line 22, in init
File "videotrans\recognition\_qwen3asr.py", line 18, in post_init
File "videotrans\recognition\_base.py", line 208, in cut_audio
IndexError: list index out of range
TaskCfgVTT(uuid='dc9b8c47a1', name='C:/Users/Administrator/Downloads/Study_30min_DataCollection_2026-04-19_Joseph_1080p.mp4', dirname='C:/Users/Administrator/Downloads', noextname='Study_30min_DataCollection_2026-04-19_Joseph_1080p', basename='Study_30min_DataCollection_2026-04-19_Joseph_1080p.mp4', ext='mp4', target_dir='Study_30min_DataCollection_2026-04-19_Joseph_1080p-mp4', cache_folder='F:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22752/dc9b8c47a1', is_cuda=False, source_language='英语', source_language_code='en', source_sub='Study_30min_DataCollection_2026-04-19_Joseph_1080p-mp4/en.srt', source_wav='F:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22752/dc9b8c47a1/en.wav', source_wav_output='Study_30min_DataCollection_2026-04-19_Joseph_1080p-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='Study_30min_DataCollection_2026-04-19_Joseph_1080p-mp4/zh-cn.srt', target_wav='F:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22752/dc9b8c47a1/target.wav', target_wav_output='Study_30min_DataCollection_2026-04-19_Joseph_1080p-mp4/zh-cn.m4a', translate_type=4, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Yunjian(Male/CN)', voice_autorate=True, video_autorate=True, remove_silent_mid=False, align_sub_audio=True, detect_language='en', recogn_type=7, model_name='tiny', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=1, fix_punc=0, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='Study_30min_DataCollection_2026-04-19_Joseph_1080p-mp4/Study_30min_DataCollection_2026-04-19_Joseph_1080p.mp4', novoice_mp4='F:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22752/dc9b8c47a1/novoice.mp4', is_separate=False, embed_bgm=True, instrument=None, vocal='F:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22752/dc9b8c47a1/vocal.wav', clear_cache=True, background_music='', subtitle_type=0, 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:F:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612

1 Replies

核心原因

这是 Qwen3-ASR(阿里百炼本地语音识别)在音频预分割阶段抛出的异常。list index out of range 表示 VAD(语音活动检测)切割后的音频片段列表为空,尝试获取第一个片段时越界。通常由下述原因之一引起:

  1. 提取的音频文件为空或损坏(视频无有效音轨,或原始音频解码失败)。
  2. 音频音量极低或完全静音,VAD 未检测到任何有效语音段。
  3. 临时音频文件路径异常(如文件名过长、特殊字符导致写入失败)。

解决步骤

  1. 验证视频文件完整性
    用本地播放器(如 VLC)打开原视频,确认能正常听到人声。若无声,请更换有音轨的视频。
  2. 清理缓存并重试
    返回主界面,勾选 “清理已生成” 后重新执行,避免上次的损坏缓存干扰。
  3. 更换 ASR 渠道(推荐)

    • 当前选择的 Qwen3-ASR(本地) 对中文音频效果较好,但你的视频是英文发音。建议改选 faster-whisper(本地) + large-v3 模型,对英文支持更稳定。
    • 步骤:在主界面第二行“语音识别渠道”下拉框中切换,模型选择 large-v3(需确保足够显存)。
  4. 检查是否启用 CUDA 加速
    你的日志显示 is_cuda=False。若你拥有 NVIDIA 显卡且已正确安装 CUDA 12.8+ 和 cuDNN 9.11+,请勾选 “CUDA 加速” 提升处理稳定性。
  5. 尝试延长 VAD 静音阈值
    进入 菜单 -> 工具 -> 高级选项 -> 语音识别参数,将 “最长语音持续(秒)” 设为 10“静音分割持续毫秒” 设为 1000,然后重试。

请查阅相关文档:

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

Similar issues already exist