Kedreamix / Linly-Dubbing

智能视频多语言AI配音/翻译工具 - Linly-Dubbing — “AI赋能,语言无界”
Apache License 2.0
1.42k stars 117 forks source link

人声分离后面的都不行T-T #26

Open qjlswat opened 6 days ago

qjlswat commented 6 days ago

已经死磕了两天,都没解决,我不想放弃(本人编程零基础,这是第一次尝试在github下项目玩)。希望大佬给我想想解决办法,叩谢了~出现了以下的情况: (linly_dubbing) C:\Users\nuomic\Linly-Dubbing>python webui.py C:\Users\nuomic\anaconda3\envs\linly_dubbing\lib\site-packages\pyannote\audio\core\io.py:43: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call. torchaudio.set_audio_backend("soundfile") failed to import ttsfrd, use WeTextProcessing instead Running on local URL: http://127.0.0.1:6006 Running on public URL: https://7bb2210d5146e73302.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run gradio deploy from Terminal to deploy to Spaces (https://huggingface.co/spaces) 2024-09-12 20:55:22.064 | INFO | tools.step010_demucs_vr:load_model:21 - Loading Demucs model: htdemucs_ft 2024-09-12 20:55:22.068 | INFO | tools.step042_tts_xtts:load_model:24 - Loading TTS model from models/TTS/XTTS-v2 Loading TTS model from models/TTS/XTTS-v2 2024-09-12 20:55:22.070 | INFO | tools.step021_asr_whisperx:load_whisper_model:36 - Loading WhisperX model: models/ASR/whisper\faster-whisper-large-v3

Using model: xtts 2024-09-12 20:55:32.083 | ERROR | tools.step021_asr_whisperx:load_diarize_model:71 - Failed to load diarization model in 10.01s due to An error happened while trying to locate the file on the Hub and we cannot find the requested files in the local cache. Please check your connection and try again or make sure your Internet connection is on. 2024-09-12 20:55:32.084 | INFO | tools.step021_asr_whisperx:load_diarize_model:72 - You have not set the HF_TOKEN, so the pyannote/speaker-diarization-3.1 model could not be downloaded. 2024-09-12 20:55:32.085 | INFO | tools.step021_asr_whisperx:load_diarize_model:73 - If you need to use the speaker diarization feature, please request access to the pyannote/speaker-diarization-3.1 model. Alternatively, you can choose not to enable this feature. 2024-09-12 20:55:35.098 | INFO | tools.step010_demucs_vr:load_model:25 - Demucs model loaded in 13.03 seconds 2024-09-12 20:55:41.815 | INFO | tools.step042_tts_xtts:load_model:35 - TTS model loaded in 19.75s [BiliBili] Extracting URL: https://www.bilibili.com/video/BV1kr421M7vz/ [BiliBili] 1kr421M7vz: Downloading webpage [BiliBili] BV1kr421M7vz: Extracting videos in anthology [BiliBili] Format(s) 4K 超清, 1080P 高码率, 1080P 高清, 720P 高清 are missing; you have to login or become a premium member to download them. Use --cookies-from-browser or --cookies for the authentication. See https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp for how to manually pass cookies [BiliBili] 1406337061: Extracting chapters 2024-09-12 20:55:42.947 | INFO | tools.step000_video_downloader:download_single_video:35 - Video already downloaded in videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:55:42.949 | INFO | tools.do_everything:process_video:43 - Process video in videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:55:42.952 | INFO | tools.step010_demucs_vr:separate_all_audio_under_folder:114 - Audio already separated in videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:55:42.952 | INFO | tools.step010_demucs_vr:separate_all_audio_under_folder:115 - All audio separated under videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:55:42.953 | INFO | tools.step020_asr:transcribe_audio:70 - Transcribing videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候\audio_vocals.wav 2024-09-12 20:55:42.954 | INFO | tools.step021_asr_whisperx:load_whisper_model:36 - Loading WhisperX model: models/ASR/whisper\faster-whisper-large-v3 2024-09-12 20:55:57.655 | ERROR | tools.do_everything:process_video:60 - Error processing video (英文无字幕) 阿里这小子在水城威尼斯发来问候: Requested float16 compute type, but the target device or backend do not support efficient float16 computation. 2024-09-12 20:55:57.681 | INFO | tools.step000_video_downloader:download_single_video:35 - Video already downloaded in videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:55:57.682 | INFO | tools.do_everything:process_video:43 - Process video in videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:55:57.686 | INFO | tools.step010_demucs_vr:separate_all_audio_under_folder:114 - Audio already separated in videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:55:57.687 | INFO | tools.step010_demucs_vr:separate_all_audio_under_folder:115 - All audio separated under videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:55:57.689 | INFO | tools.step020_asr:transcribe_audio:70 - Transcribing videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候\audio_vocals.wav 2024-09-12 20:55:57.694 | INFO | tools.step021_asr_whisperx:load_whisper_model:36 - Loading WhisperX model: models/ASR/whisper\faster-whisper-large-v3 2024-09-12 20:56:00.773 | ERROR | tools.do_everything:process_video:60 - Error processing video (英文无字幕) 阿里这小子在水城威尼斯发来问候: Requested float16 compute type, but the target device or backend do not support efficient float16 computation. 2024-09-12 20:56:00.775 | INFO | tools.step000_video_downloader:download_single_video:35 - Video already downloaded in videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:56:00.777 | INFO | tools.do_everything:process_video:43 - Process video in videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:56:00.778 | INFO | tools.step010_demucs_vr:separate_all_audio_under_folder:114 - Audio already separated in videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:56:00.779 | INFO | tools.step010_demucs_vr:separate_all_audio_under_folder:115 - All audio separated under videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候 2024-09-12 20:56:00.780 | INFO | tools.step020_asr:transcribe_audio:70 - Transcribing videos\村长台钓加拿大\20240805 英文无字幕 阿里这小子在水城威尼斯发来问候\audio_vocals.wav 2024-09-12 20:56:00.781 | INFO | tools.step021_asr_whisperx:load_whisper_model:36 - Loading WhisperX model: models/ASR/whisper\faster-whisper-large-v3 2024-09-12 20:56:03.838 | ERROR | tools.do_everything:process_video:60 - Error processing video (英文无字幕) 阿里这小子在水城威尼斯发来问候: Requested float16 compute type, but the target device or backend do not support efficient float16 computation. 编程Snipaste_2024-09-12_20-57-23