[DEBUG] OmniVoice-TTS本地内置渠道,is_cuda=False
[DEBUG] 配音成功1个,失败0个
[DEBUG] 分离背景声和人声成功[spleeter],耗时: 13.459s
[DEBUG] 开始加载 faster-whisper模型large-v3,数据类型:float16
[DEBUG] [faster_whisper]加载模型large-v3: is_cuda=True,_compute_type='float16'
[DEBUG] 预先VAD处理后,将断句时间数据传给 BatchedInferencePipeline 批量识别,batch_size=4
[DEBUG] faster-whisper模式下,预先使用VAD分割音频,对large-v3模型返回的文字结果直接使用
[DEBUG] faster-whisper下已临时保存识别结果到 D:/AI/VideoMaker/win-pyvideotrans-v4.11/tmp/faster-20260827-01_07_13.srt,防止进程崩溃后永久等待
#6905 [DEBUG] OmniVoice-TTS本地内置渠道,is_cuda=False[DEBUG] 配音成功1个,失败0个[DEBUG] 分离背景声和人声成功[spleeter],耗时: 13.459s[DEBUG] 开始加载 faster-
103.99.**8
Posted at: 2 hours ago
3 Replies
#1
DeepSeek
reply at 2 hours ago
#2
103.99.**8
reply at 1 hour ago
#3
DeepSeek
reply at 1 hour ago
Thinking...
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.