#6945 配音阶段出错 [Higgs-audio-v3(内置)] Audio must be mono, but got 2,Traceback (most recent call last): File

配音阶段出错 [Higgs-audio-v3(内置)] Audio must be mono, but got 2,Traceback (most recent call last):
File "videotrans\process\higgs_tts.py", line 94, in higgs_fun
File "D:\TTS\win-pyvideotrans-v4.11\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\TTS\win-pyvideotrans-v4.11\models\modules\transformers_modules\models_hyphen__hyphen_multimodalart_hyphen__hyphen_higgs_hyphen_audio_hyphen_v3_hyphen_tts_hyphen_4b_hyphen_transformers\modeling_higgs_multimodal_qwen3.py", line 342, in generate_speech

codes_TN = self._encode_reference(reference_audio, sr)

File "D:\TTS\win-pyvideotrans-v4.11\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\TTS\win-pyvideotrans-v4.11\models\modules\transformers_modules\models_hyphen__hyphen_multimodalart_hyphen__hyphen_higgs_hyphen_audio_hyphen_v3_hyphen_tts_hyphen_4b_hyphen_transformers\modeling_higgs_multimodal_qwen3.py", lin
......
videotrans\tts\_higgs.py", line 41, in _exec

File "videotrans\configure\base.py", line 270, in _new_process

videotrans.configure.excepts.VideoTransError: Audio must be mono, but got 2,Traceback (most recent call last):
File "videotrans\process\higgs_tts.py", line 94, in higgs_fun
File "D:\TTS\win-pyvideotrans-v4.11\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\TTS\win-pyvideotrans-v4.11\models\modules\transformers_modules\models_hyphen__hyphen_multimodalart_hyphen__hyphen_higgs_hyphen_audio_hyphen_v3_hyphen_tts_hyphen_4b_hyphen_transformers\modeling_higgs_multimodal_qwen3.py", line 342, in generate_speech

codes_TN = self._encode_reference(reference_audio, sr)

File "D:\TTS\win-pyvideotrans-v4.11\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\TTS\win-pyvideotrans-v4.11\models\modules\transformers_modules\models_hyphen__hyphen_multimodalart_hyphen__hyphen_higgs_hyphen_audio_hyphen_v3_hyphen_tts_hyphen_4b_hyphen_transformers\modeling_higgs_multimodal_qwen3.py", line 261, in _encode_reference

codes_BNT = codec.encode(wav).audio_codes

File "D:\TTS\win-pyvideotrans-v4.11\_internal\transformers\models\higgs_audio_v2_tokenizer\modeling_higgs_audio_v2_tokenizer.py", line 534, in encode

raise ValueError(f"Audio must be mono, but got {channels}")

ValueError: Audio must be mono, but got 2
[DubbingSrt]语音合成: self.out_ext='wav',self.is_multi_role=False
[TaskCfgTTS]
原始输入文件名: C:/Users/Z420-Win-11/Documents/0048-zh-CN-副本 - 副本.srt,
输出结果保存到文件夹: D:/TTS/win-pyvideotrans-v4.11/output/tts,
临时文件夹: D:/TTS/win-pyvideotrans-v4.11/tmp/12140/3cbfd85288
已启用CUDA加速
配音渠道:Higgs-audio-v3(内置), 角色:yingyufanben.wav, 配音语言:zh-cn
音量:+0%, 语速:+0%, 未选 音频加速
未选 移除字幕间空隙, 未选 强制对齐字幕和声音
代理地址:http://127.0.0.1:10808