提示 This model doesn't have language tokens so it can't perform lang id

heiheiheibj commented 11 months ago

python scripts/long_audio_transcribe.py --languages "CJ" --whisper_size large <generator object _walk at 0x7f3b9dec0820> ['gdg_4.wav', 'gdg_1.wav', 'gdg_5.wav', 'gdg_2.wav', 'gdg_8.wav', 'gdg_9.wav', 'gdg_7.wav', 'gdg_6.wav', 'gdg_3.wav'] filelist= ['gdg_4.wav', 'gdg_1.wav', 'gdg_5.wav', 'gdg_2.wav', 'gdg_8.wav', 'gdg_9.wav', 'gdg_7.wav', 'gdg_6.wav', 'gdg_3.wav'] transcribing ./denoised_audio/gdg_4.wav...

Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Traceback (most recent call last): File "/home/ubuntu/VITS-fast-fine-tuning/scripts/long_audio_transcribe.py", line 45, in result = model.transcribe(parent_dir + file, word_timestamps=True, *transcribeoptions) File "/root/anaconda3/envs/barkvoice/lib/python3.10/site-packages/whisper/transcribe.py", line 130, in transcribe , probs = model.detect_language(mel_segment) File "/root/anaconda3/envs/barkvoice/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, **kwargs) File "/root/anaconda3/envs/barkvoice/lib/python3.10/site-packages/whisper/decoding.py", line 40, in detect_language raise ValueError( ValueError: This model doesn't have language tokens so it can't perform lang id

已经下载过 wget https://huggingface.co/spaces/sayashi/vits-uma-genshin-honkai/resolve/main/model/D_0-p.pth -O ./pretrained_models/D_0.pth wget https://huggingface.co/spaces/sayashi/vits-uma-genshin-honkai/resolve/main/model/G_0-p.pth -O ./pretrained_models/G_0.pth wget https://huggingface.co/spaces/sayashi/vits-uma-genshin-honkai/resolve/main/model/config.json -O ./configs/finetune_speaker.json

以前是可跑的，重装了UBUNTU 22.04就出现这问题了。谢谢