KeyError : 'vocab_size'

[chenzuozhou]

Reports keyerror when generate audio

Traceback (most recent call last): File "/data/mfsshare/thirdpart_tools/bark-with-voice-clone/test/basic.py", line 6, in preload_models(path="/data/mfsshare/models/bark/text.pt") File "/root/miniconda3/envs/bark-with-voice-clone/lib/python3.9/site-packages/bark/generation.py", line 369, in preloadmodels = load_model( File "/root/miniconda3/envs/bark-with-voice-clone/lib/python3.9/site-packages/bark/generation.py", line 322, in load_model model = _load_model_f(ckpt_path, device) File "/root/miniconda3/envs/bark-with-voice-clone/lib/python3.9/site-packages/bark/generation.py", line 228, in _load_model model_args["input_vocab_size"] = model_args["vocab_size"] KeyError: 'vocab_size'

test python script from bark import SAMPLE_RATE, generate_audio, preload_models from scipy.io.wavfile import write as write_wav

from IPython.display import Audio

download and load all models

preload_models(path="/data/mfsshare/models/bark")

generate audio from text

text_prompt = """ Hello, my name is Suno. And, uh - I like pizza. [laughs] But I also have other interests such as playing tic tac toe. """ audio_array = generate_audio(text_prompt)

save audio to disk

write_wav("bark_generation.wav", SAMPLE_RATE, audio_array)

[JonathanFly]

try to find text.pt on your hard drive and delete it. It may be a corrupt download.

[chenzuozhou]

try to find text.pt on your hard drive and delete it. It may be a corrupt download. I have confirmed the text.pt is correct, and it can run success on transformers usage, but report this err on suno usage